require(rio)
require(tidyverse)
require(xgboost)
require(ggrepel)
require(cowplot)

Loading required package: xgboost


Attaching package: ‘xgboost’


The following object is masked from ‘package:dplyr’:

    slice


Loading required package: ggrepel

Loading required package: cowplot


Attaching package: ‘cowplot’


The following object is masked from ‘package:lubridate’:

    stamp

bad = as_tibble(import("../Genetics/G25/Data/CSV/Eurasia/G25_BA.csv"))
iad = as_tibble(import("../Genetics/G25/Data/CSV/Eurasia/G25_IA.csv"))
mad = as_tibble(import("../Genetics/G25/Data/CSV/Eurasia/G25_MA.csv"))
mod = as_tibble(import("../Genetics/G25/Data/CSV/Eurasia/Global25_PCA_modern_scaled.txt"))

head(bad,1)
head(iad,1)
head(mad,1)
head(mod,1)

colnames(mod) = colnames(bad)
myptrna = "^.+(?=:)"
myptrnb = "^\\w+?_\\w+?(?=[_:\\.])"
mod = mod %>% mutate(sample = str_extract(sample,myptrna))
bad = bad %>% mutate(sample = str_extract(sample,myptrnb))
iad = iad %>% mutate(sample = str_extract(sample,myptrnb))
mad = mad %>% mutate(sample = str_extract(sample,myptrnb))

mod %>% count(sample,sort = TRUE) %>% head(20)

bad %>% count(sample,sort = TRUE) %>% head(10)

iad %>% count(sample,sort = TRUE) %>% head(10)

mad %>% count(sample,sort = TRUE) %>% head(10)

ppl = as_tibble(import("../Genetics/G25/Data/People/All.txt"))

ppl

smpls = as_tibble(import("../Genetics/G25/Data/TXT/By Country/Averages/Modern_averages.txt"))

nrow(smpls)
smpls %>% sample_n(10)

myfun = function (mydf,e = 0.75,d = 5,a = 0.5,g = 0,l = 0.5) {
        mydata = mydf %>% mutate(label = as.numeric(as.factor(sample)) - 1) %>% select(-sample)
        nclas = length(unique(mydata$label))
        print(paste0("Number of classes: ",nclas))
        smpl = sample(1:nrow(mydata),.75*nrow(mydata))
        print("Split into test and train samples")
        train_data = mydata[smpl,]
        test_data = mydata[-smpl,]
        print(dim(train_data))
        print(dim(test_data))
        td = data.matrix(train_data %>% select(-label))
        tl = train_data$label
        ttd = data.matrix(test_data %>% select(-label))
        ttl = test_data$label
        dtrain = xgb.DMatrix(data = td,label = tl)
        dtest = xgb.DMatrix(data = ttd,label = ttl)
        print("Starting XGBoost training")
        obj = "multi:softprob"
        mymod = xgb.train(data = dtrain,
                          eta = e,
                          max_depth = d,
                          nround = 100,
                          subsample = .5,
                          colsample_bytree = .5,
                          alpha = a,
                          gamma = g,
                          lambda = l,
                          objective = obj,
                          num_class = nclas,
                          nthread = 4,
                          watchlist = list(train = dtrain,test = dtest),
                          print_every_n = 25,
                          verbose = 1)
        mypred = predict(mymod,dtest)
        nclas = ifelse(str_ends(obj,"max"),1,nclas)
        mypred = mypred %>% matrix(ncol = nclas,byrow = TRUE) %>% as_tibble() %>% mutate(row = row_number()) %>% bind_cols(label = ttl)
        colnames(mypred) = c(as.character(0:(nclas-1)),"row","label")
        myd = pivot_longer(mypred,cols = !matches("^[rl]"),names_to = "variable",values_to = "value")
        myd = myd %>% group_by(row,label) %>% mutate(maxval = max(value)) %>% ungroup()
        mydd = myd %>% dplyr::filter(value == maxval)
        print(sample_n(mydd,15))
        err = with(mydd,mean(label != variable))
        print(paste0("test-error = ", err))
        return(mymod)
    }

mypfun = function(mymdl,mypd,mynd,verbose = TRUE) {
    smpls = unique(na.omit(mypd$sample))
    #nclas = 1
    nclas = length(smpls)
    print(paste0("Using ",nclas," populations"))
    mypred = predict(mymdl,xgb.DMatrix(data = data.matrix(mynd %>% select(-V1)),label = 1:nrow(mynd)))
    mypred = mypred %>% matrix(ncol = nclas,byrow = TRUE) %>% as_tibble() %>% mutate(row = row_number())
    colnames(mypred) = c(as.character(0:(nclas-1)),"row")
    myd = pivot_longer(mypred,cols = !matches("^row"),names_to = "variable",values_to = "value")
#    myd = myd %>% group_by(row) %>% mutate(tot = sum(value)) %>% mutate(value = value/tot) %>% ungroup() 
    mprd = myd %>% inner_join(mynd %>% select(V1) %>% mutate(row = row_number()),by = "row") %>% 
            inner_join(data.frame(variable = as.character(1:length(smpls)),eth = smpls))
    mprd = mprd %>% mutate(name = str_extract(V1,"^.+(?=:)")) %>% select(name,eth,value)
    if(verbose) print(mprd %>% dplyr::filter(value >= 0.02) %>% 
                          mutate(value = paste0(round(100*value,2),"%")) %>% 
                          arrange(name,desc(value)) %>% as.data.frame)
    return(mprd)
}

mypfun2 = function(mymdl,mypd,mynd) {
    mprd = mypfun(mymdl,mypd,mynd,verbose = FALSE)
    for(ii in 1:999) {
        mprd = bind_rows(mprd,mypfun(mymdl,mypd,mynd,verbose = FALSE))
    }
    mprd = mprd %>% group_by(name,eth) %>% summarize(value = round(100*mean(value))) %>% 
                    arrange(name,desc(value)) %>% dplyr::filter(value >= 2)
    return(mprd)
    }

mythm = theme_minimal_hgrid(7,color = "gray45",line_size = 0.1) + theme(plot.background = element_rect(fill = "gray20"))

plotfun = function(mydata,lsz = 2,nrw = 1) {
    ggplot(mydata,aes(as.numeric(str_remove(value,"%")),I(1))) + 
        geom_label_repel(stat = "identity",aes(label = eth,fill = as.numeric(as.factor(name))),size = lsz,force = 4) + 
        scale_x_log10() + 
        facet_wrap(facets = ~ name,nrow = nrw) + 
        #coord_cartesian(ylim = c(3,8)) + 
        coord_flip() + 
        guides(fill = "none") + 
        scale_fill_distiller() + 
        #scale_fill_viridis_c(option = "H") + 
        mythm + xlab("%") + ylab("") + 
        theme(axis.text.x = element_blank(),axis.line.x = element_blank(),axis.ticks.x = element_blank())
    }

plotfun2 = function(mydata,nrw = 1) {
    ggplot(mydata,aes(reorder(eth,value),value)) + 
        geom_bar(aes(fill = value),stat = "identity") + 
        facet_wrap(~ name,nrow = nrw) + 
        scale_fill_viridis_c("G") + 
        coord_flip() + xlab("") + ylab("") + 
        mythm + guides(fill = "none") + 
        theme(axis.text = element_text(size = 4,color = "wheat"))
    }

plotfun3 = function(mprd) {
    p1 = plotfun(mprd,lsz = 1.5)
    p2 = plotfun2(mprd)
    options(repr.plot.width = 8, repr.plot.height = 4, repr.plot.res = 400)
    plot_grid(p1,p2,labels = c('A','B'),label_size = 10)
    }

mdl = myfun(na.omit(mod),e = 0.5,a = 1,l = 10)

[1] "Number of classes: 391"
[1] "Split into test and train samples"
[1] 3582   26
[1] 1194   26
[1] "Starting XGBoost training"
[1]	train-mlogloss:5.537399	test-mlogloss:5.584334 
[26]	train-mlogloss:2.314773	test-mlogloss:3.408938 
[51]	train-mlogloss:1.477313	test-mlogloss:3.049051 
[76]	train-mlogloss:1.096387	test-mlogloss:2.913518 
[100]	train-mlogloss:0.900769	test-mlogloss:2.862833 
# A tibble: 15 × 5
     row label variable  value maxval
   <int> <dbl> <chr>     <dbl>  <dbl>
 1   238    82 82       0.617  0.617 
 2  1023   334 317      0.0879 0.0879
 3   981   311 47       0.204  0.204 
 4   147    55 56       0.382  0.382 
 5   298    91 236      0.0383 0.0383
 6   975   306 28       0.604  0.604 
 7   814   248 9        0.475  0.475 
 8   720   217 168      0.0776 0.0776
 9   759   230 230      0.197  0.197 
10  1058   342 342      0.918  0.918 
11   648   190 190      0.452  0.452 
12   105    43 39       0.134  0.134 
13   882   271 91       0.0270 0.0270
14    31    12 12       0.108  0.108 
15   773   238 275      0.131  0.131 
[1] "test-error = 0.622278056951424"

mprd = mypfun(mdl,mod,ppl)

[1] "Using 391 populations"

Joining with `by = join_by(variable)`

   name                   eth  value
1    MD      Ashkenazi_Poland  6.93%
2    MD   Ashkenazi_Lithuania  6.08%
3    MD         Armenian_Urfa  3.58%
4    MD      Ashkenazi_Russia 29.79%
5    MD     Ashkenazi_Germany   2.1%
6    MN   Ashkenazi_Lithuania 71.82%
7    MN  Ashkenazi_Belarussia  2.83%
8    RN   Ashkenazi_Lithuania 48.98%
9    RN      Ashkenazi_Russia 31.07%
10   RN      Ashkenazi_Poland  2.01%
11   TP   Russian_Leshukonsky  9.94%
12   TP Ukrainian_Zakarpattia  9.69%
13   TP        Russian_Ryazan  6.68%
14   TP       Ukrainian_Rivne   3.1%
15   TP                Bedzan  2.59%
16   TP   Ukrainian_Chernihiv  2.27%
17   TP        Ukrainian_Lviv  2.12%

mprd = mypfun2(mdl,mod,ppl)

[1] "Using 391 populations"

Joining with `by = join_by(variable)`

[1] "Using 391 populations"

Joining with `by = join_by(variable)`

[1] "Using 391 populations"

Joining with `by = join_by(variable)`

[1] "Using 391 populations"

Joining with `by = join_by(variable)`

[1] "Using 391 populations"

Joining with `by = join_by(variable)`

plotfun3(mprd)

#mod = mod %>% mutate(sample = ifelse(str_detect(sample,"_"),str_extract(sample,"^\\w+?(?=_)"),sample))
#modd = mod %>% mutate(sample = ifelse(str_detect(sample,"Ukrain|Lithuan|Ashken|Italian|Spani|Greek|Georgi|Irani|Turki|Frenc|Azerb|Armeni|Basqu"),str_extract(sample,"^\\w+?(?=_)"),sample))
#modd = mod %>% mutate(sample = ifelse(str_detect(sample,"Ukrain|Lithuan|Ashken|Georgi|Azerb|Armeni|Basqu"),str_extract(sample,"^\\w+?(?=_)"),sample))
modd = mod %>% dplyr::filter(!str_detect(sample,"^(Elmo|Tat|Roma|Alta|Aeta|Bata|Erit|Mongo|Saami|Shor|Satna)")) %>% na.omit()
mdl = myfun(modd,e = 0.5,a = 1,l = 10)

[1] "Number of classes: 357"
[1] "Split into test and train samples"
[1] 3361   26
[1] 1121   26
[1] "Starting XGBoost training"
[1]	train-mlogloss:5.457783	test-mlogloss:5.533315 
[26]	train-mlogloss:2.260892	test-mlogloss:3.340530 
[51]	train-mlogloss:1.439845	test-mlogloss:2.993087 
[76]	train-mlogloss:1.067836	test-mlogloss:2.872749 
[100]	train-mlogloss:0.868774	test-mlogloss:2.809086 
# A tibble: 15 × 5
     row label variable  value maxval
   <int> <dbl> <chr>     <dbl>  <dbl>
 1   257    79 79       0.504  0.504 
 2    97    32 7        0.100  0.100 
 3   572   173 241      0.0866 0.0866
 4   368   104 180      0.317  0.317 
 5   338    97 97       0.350  0.350 
 6   571   173 174      0.171  0.171 
 7    79    28 28       0.530  0.530 
 8   116    41 38       0.397  0.397 
 9   659   196 180      0.323  0.323 
10    24     8 8        0.278  0.278 
11    83    28 28       0.291  0.291 
12  1100   351 351      0.265  0.265 
13   799   232 232      0.186  0.186 
14   447   131 150      0.139  0.139 
15   149    52 97       0.255  0.255 
[1] "test-error = 0.661909009812667"

modd$sample %>% unique %>% sort

mprd = mypfun(mdl,modd,ppl)

[1] "Using 357 populations"

Joining with `by = join_by(variable)`

   name                   eth  value
1    MD      Ashkenazi_Poland  5.04%
2    MD      Ashkenazi_Russia 37.66%
3    MD         Armenian_Urfa  3.77%
4    MD   Ashkenazi_Lithuania 10.94%
5    MN      Ashkenazi_Russia   7.5%
6    MN   Ashkenazi_Lithuania 55.13%
7    MN  Ashkenazi_Belarussia  3.26%
8    RN   Ashkenazi_Lithuania  45.6%
9    RN      Ashkenazi_Russia 28.44%
10   TP Ukrainian_Zakarpattia  5.53%
11   TP   Russian_Leshukonsky  4.51%
12   TP               Cypriot  3.48%
13   TP        Russian_Ryazan  3.26%
14   TP           Palestinian  2.51%
15   TP       Ukrainian_Rivne  2.33%

mprd = mypfun2(mdl,modd,ppl)

[1] "Using 357 populations"

Joining with `by = join_by(variable)`

[1] "Using 357 populations"

Joining with `by = join_by(variable)`

[1] "Using 357 populations"

Joining with `by = join_by(variable)`

[1] "Using 357 populations"

Joining with `by = join_by(variable)`

[1] "Using 357 populations"

Joining with `by = join_by(variable)`

plotfun3(mprd)

Warning message:
“ggrepel: 8 unlabeled data points (too many overlaps). Consider increasing max.overlaps”

mdl = myfun(na.omit(bad),e = 1,a = 1,l = 10)

[1] "Number of classes: 233"
[1] "Split into test and train samples"
[1] 1068   26
[1] 357  26
[1] "Starting XGBoost training"
[1]	train-mlogloss:4.909506	test-mlogloss:4.935734 
[26]	train-mlogloss:2.258924	test-mlogloss:3.350156 
[51]	train-mlogloss:1.755150	test-mlogloss:3.263681 
[76]	train-mlogloss:1.526543	test-mlogloss:3.258402 
[100]	train-mlogloss:1.389339	test-mlogloss:3.234205 
# A tibble: 15 × 5
     row label variable  value maxval
   <int> <dbl> <chr>     <dbl>  <dbl>
 1    86    31 27       0.605  0.605 
 2   127    57 177      0.316  0.316 
 3   167    95 166      0.0758 0.0758
 4    13    11 132      0.0482 0.0482
 5    44    26 26       0.0758 0.0758
 6   253   165 87       0.248  0.248 
 7    99    32 27       0.768  0.768 
 8   242   158 161      0.0912 0.0912
 9   328   208 210      0.194  0.194 
10    69    27 27       0.935  0.935 
11    60    27 27       0.453  0.453 
12   209   137 137      0.977  0.977 
13   282   182 182      0.105  0.105 
14   181   115 163      0.162  0.162 
15   212   137 137      0.849  0.849 
[1] "test-error = 0.641456582633053"

mprd = mypfun(mdl,bad,ppl)

[1] "Using 233 populations"

Joining with `by = join_by(variable)`

  name              eth  value
1   TP Czech_CordedWare 77.29%
2   TP       Poland_TRB 13.86%

mprd = mypfun2(mdl,bad,ppl)

[1] "Using 233 populations"

Joining with `by = join_by(variable)`

[1] "Using 233 populations"

Joining with `by = join_by(variable)`

[1] "Using 233 populations"

Joining with `by = join_by(variable)`

[1] "Using 233 populations"

Joining with `by = join_by(variable)`

[1] "Using 233 populations"

Joining with `by = join_by(variable)`

plotfun3(mprd)

mprd = mypfun(mdl,bad,smpls)

[1] "Using 225 populations"

Joining with `by = join_by(variable)`

                     name                     eth value
1    Ashkenazi_Belarussia     Bulgaria_BeliBreyag  4.8%
2    Ashkenazi_Belarussia             Lebanon_MBA  2.3%
3    Ashkenazi_Belarussia             Hungary_MBA  1.5%
4    Ashkenazi_Belarussia Ukraine_GlobularAmphora  1.4%
5    Ashkenazi_Belarussia             Armenia_MBA  1.2%
6     Ashkenazi_Lithuania             Lebanon_MBA  2.2%
7     Ashkenazi_Lithuania        Armenia_Lchashen  1.6%
8     Ashkenazi_Lithuania             Hungary_MBA  1.6%
9     Ashkenazi_Lithuania     Bulgaria_BeliBreyag  1.5%
10    Ashkenazi_Lithuania Ukraine_GlobularAmphora  1.4%
11    Ashkenazi_Lithuania      Slovakia_Mikusovce  1.3%
12    Ashkenazi_Lithuania             Armenia_MBA  1.2%
13    Ashkenazi_Lithuania            Iran_Hasanlu  1.1%
14      Ashkenazi_Ukraine             Lebanon_MBA  2.2%
15      Ashkenazi_Ukraine        Armenia_Lchashen  1.9%
16      Ashkenazi_Ukraine     Bulgaria_BeliBreyag  1.8%
17      Ashkenazi_Ukraine             Hungary_MBA  1.5%
18      Ashkenazi_Ukraine Ukraine_GlobularAmphora  1.4%
19      Ashkenazi_Ukraine             Armenia_MBA  1.2%
20      Ashkenazi_Ukraine            Iran_Hasanlu  1.2%
21             Belarusian         Netherlands_MBA 16.5%
22             Belarusian              Croatia_BA  4.4%
23             Belarusian      Germany_CordedWare  4.2%
24             Belarusian Germany_SouthernGermany  2.9%
25             Belarusian             Hungary_EBA  2.6%
26             Belarusian              Serbia_LBA  2.1%
27             Belarusian             Levant_Ebla  1.8%
28             Belarusian        Czech_CordedWare  1.6%
29             Belarusian           Bahamas_Taino  1.6%
30             Belarusian              Poland_EBA  1.4%
31             Belarusian         Russia_Sosnoviy  1.3%
32             Belarusian              Syria_Ebla  1.3%
33             Belarusian     Kyrgyzstan_TianShan  1.2%
34             Belarusian           Greece_Minoan  1.1%
35             Belarusian              Russia_MBA  1.1%
36                Bosnian        Czech_CordedWare 38.5%
37                Bosnian         Croatia_Vucedol  2.9%
38                Bosnian           Greece_Minoan  1.9%
39                Bosnian              Croatia_BA  1.9%
40                Bosnian              Serbia_LBA  1.6%
41                Bosnian      Turkey_Hellenistic  1.4%
42                Bosnian             Germany_EBA  1.1%
43      Cossack_Ukrainian        Czech_CordedWare 21.2%
44      Cossack_Ukrainian         Netherlands_MBA  7.9%
45      Cossack_Ukrainian              Croatia_BA  4.1%
46      Cossack_Ukrainian              Poland_EBA  1.4%
47      Cossack_Ukrainian             Hungary_EBA  1.3%
48      Cossack_Ukrainian           Greece_Minoan  1.2%
49      Cossack_Ukrainian      Germany_CordedWare  1.1%
50      Cossack_Ukrainian Germany_SouthernGermany  1.1%
51      Cossack_Ukrainian             Levant_Ebla  1.1%
52               Croatian        Czech_CordedWare 77.1%
53                  Czech        Czech_CordedWare 69.4%
54               Estonian         Netherlands_MBA 94.8%
55                Ingrian         Netherlands_MBA 65.8%
56                Ingrian              Poland_EBA  2.5%
57                Ingrian      Germany_CordedWare  1.3%
58               Karelian         Netherlands_MBA 62.1%
59               Karelian        Czech_CordedWare  3.2%
60               Karelian         Russia_Sosnoviy  1.7%
61               Karelian      Germany_CordedWare  1.6%
62               Karelian              Poland_EBA  1.4%
63                    Lak             Armenia_EBA 10.4%
64                    Lak         Russia_Srubnaya  6.2%
65                    Lak           Russia_Moscow  4.3%
66                    Lak        Armenia_Lchashen  1.9%
67                    Lak             Armenia_MBA  1.9%
68                    Lak          Russia_Ivanovo  1.8%
69                    Lak        Czech_BellBeaker  1.6%
70                    Lak         Russia_Buryatia  1.4%
71                    Lak             Armenia_LBA  1.2%
72                    Lak             Russia_Tver  1.2%
73                    Lak      Slovakia_Mikusovce  1.1%
74                    Lak        Armenia_Beniamin  1.1%
75                Latvian         Netherlands_MBA 93.4%
76          Lithuanian_PA         Netherlands_MBA   93%
77          Lithuanian_PZ         Netherlands_MBA 91.6%
78          Lithuanian_PZ             Hungary_EBA  1.2%
79          Lithuanian_RA         Netherlands_MBA   90%
80          Lithuanian_RA             Hungary_EBA  1.2%
81          Lithuanian_SZ         Netherlands_MBA 91.1%
82          Lithuanian_SZ             Hungary_EBA  1.2%
83          Lithuanian_VA         Netherlands_MBA 93.5%
84          Lithuanian_VZ         Netherlands_MBA 91.3%
85         North_Ossetian             Armenia_EBA 45.1%
86         North_Ossetian             Armenia_LBA 22.5%
87         North_Ossetian           Russia_Moscow    4%
88         North_Ossetian         Russia_Buryatia  3.8%
89         North_Ossetian        Armenia_Lchashen  1.2%
90               Ossetian             Armenia_EBA 47.9%
91               Ossetian         Russia_Buryatia 14.6%
92               Ossetian             Armenia_LBA  7.7%
93               Ossetian        Armenia_Beniamin    4%
94               Ossetian           Russia_Moscow  3.4%
95               Ossetian        Armenia_Lchashen  1.7%
96               Ossetian             Armenia_MBA    1%
97                 Polish        Czech_CordedWare 10.8%
98                 Polish         Netherlands_MBA  6.6%
99                 Polish              Croatia_BA  4.3%
100                Polish             Hungary_EBA  3.3%
101                Polish              Serbia_LBA  3.2%
102                Polish Germany_SouthernGermany  1.7%
103                Polish      Germany_CordedWare  1.6%
104                Polish           Greece_Minoan  1.3%
105      Polish_Kashubian         Netherlands_MBA 33.8%
106      Polish_Kashubian      Germany_CordedWare  8.7%
107      Polish_Kashubian Germany_SouthernGermany  6.2%
108      Polish_Kashubian             Hungary_EBA    5%
109      Polish_Kashubian        Czech_CordedWare  3.6%
110      Polish_Kashubian              Croatia_BA  2.1%
111      Polish_Kashubian              Serbia_LBA  1.1%
112       Polish_Silesian        Czech_CordedWare 47.9%
113       Polish_Silesian              Serbia_LBA  4.4%
114       Polish_Silesian              Croatia_BA  1.8%
115       Polish_Silesian         Croatia_Vucedol  1.6%
116      Russian_Belgorod        Czech_CordedWare 25.4%
117      Russian_Belgorod              Croatia_BA  4.2%
118      Russian_Belgorod         Netherlands_MBA  3.2%
119      Russian_Belgorod              Serbia_LBA  2.1%
120      Russian_Belgorod             Levant_Ebla  1.8%
121      Russian_Belgorod      Germany_CordedWare  1.6%
122      Russian_Belgorod             Hungary_EBA  1.6%
123      Russian_Belgorod Germany_SouthernGermany  1.6%
124      Russian_Belgorod           Greece_Minoan    1%
125      Russian_Belgorod              Syria_Ebla    1%
126      Russian_Belgorod           Bahamas_Taino    1%
127        Russian_Kaluga         Netherlands_MBA   42%
128        Russian_Kaluga      Germany_CordedWare  8.7%
129        Russian_Kaluga              Croatia_BA  2.9%
130        Russian_Kaluga           Greece_Minoan  1.8%
131        Russian_Kaluga              Serbia_LBA  1.4%
132        Russian_Kaluga        Czech_CordedWare  1.3%
133        Russian_Kaluga              Poland_EBA  1.3%
134        Russian_Kaluga             Levant_Ebla    1%
135      Russian_Kostroma         Netherlands_MBA   38%
136      Russian_Kostroma        Czech_CordedWare  8.7%
137      Russian_Kostroma      Germany_CordedWare  4.5%
138      Russian_Kostroma         Russia_Sosnoviy  2.4%
139      Russian_Kostroma              Croatia_BA  1.8%
140      Russian_Kostroma             Hungary_EBA  1.1%
141      Russian_Kostroma     Bulgaria_BeliBreyag    1%
142  Russian_Krasnoborsky         Netherlands_MBA 45.7%
143  Russian_Krasnoborsky        Czech_CordedWare    4%
144  Russian_Krasnoborsky         Russia_Sosnoviy  3.5%
145  Russian_Krasnoborsky      Germany_CordedWare  1.6%
146  Russian_Krasnoborsky              Croatia_BA  1.4%
147  Russian_Krasnoborsky             Levant_Ebla  1.4%
148         Russian_Kursk         Netherlands_MBA 18.6%
149         Russian_Kursk        Czech_CordedWare   16%
150         Russian_Kursk      Germany_CordedWare  8.8%
151         Russian_Kursk              Croatia_BA  3.4%
152         Russian_Kursk           Greece_Minoan  1.2%
153         Russian_Kursk              Serbia_LBA  1.2%
154         Russian_Kursk             Hungary_EBA  1.2%
155         Russian_Kursk              Poland_EBA  1.1%
156   Russian_Leshukonsky         Netherlands_MBA 41.7%
157   Russian_Leshukonsky             Levant_Ebla    2%
158   Russian_Leshukonsky              Russia_EBA  1.4%
159   Russian_Leshukonsky             Russia_Tver  1.1%
160   Russian_Leshukonsky         Russia_Sosnoviy  1.1%
161          Russian_Orel      Germany_CordedWare  9.5%
162          Russian_Orel        Czech_CordedWare  9.1%
163          Russian_Orel         Netherlands_MBA  5.7%
164          Russian_Orel              Croatia_BA  4.5%
165          Russian_Orel           Greece_Minoan  1.9%
166          Russian_Orel              Serbia_LBA  1.4%
167          Russian_Orel             Hungary_EBA  1.4%
168          Russian_Orel           Bahamas_Taino  1.2%
169          Russian_Orel         Russia_Sosnoviy  1.2%
170          Russian_Orel     Kyrgyzstan_TianShan  1.1%
171          Russian_Orel             Levant_Ebla  1.1%
172        Russian_Pinega         Netherlands_MBA   41%
173        Russian_Pinega         Russia_Sosnoviy  2.9%
174        Russian_Pinega              Poland_EBA  2.1%
175        Russian_Pinega              Croatia_BA  1.9%
176        Russian_Pinega      Germany_CordedWare  1.7%
177        Russian_Pinega             Levant_Ebla  1.6%
178        Russian_Pinega             Russia_Tver  1.3%
179        Russian_Pinega           Bahamas_Taino    1%
180     Russian_Pinezhsky         Netherlands_MBA 63.9%
181     Russian_Pinezhsky             Levant_Ebla    1%
182         Russian_Pskov         Netherlands_MBA 70.5%
183         Russian_Pskov         Russia_Sosnoviy  2.2%
184         Russian_Pskov              Croatia_BA  1.1%
185        Russian_Ryazan      Germany_CordedWare 16.6%
186        Russian_Ryazan         Netherlands_MBA    8%
187        Russian_Ryazan              Croatia_BA  4.5%
188        Russian_Ryazan        Czech_CordedWare  2.8%
189        Russian_Ryazan           Greece_Minoan  1.9%
190        Russian_Ryazan              Poland_EBA  1.9%
191        Russian_Ryazan             Hungary_EBA  1.4%
192        Russian_Ryazan      Slovakia_Mikusovce  1.2%
193        Russian_Ryazan              Syria_Ebla  1.1%
194      Russian_Smolensk      Germany_CordedWare 12.4%
195      Russian_Smolensk         Netherlands_MBA 10.8%
196      Russian_Smolensk              Croatia_BA  4.6%
197      Russian_Smolensk             Hungary_EBA  3.2%
198      Russian_Smolensk              Serbia_LBA  2.3%
199      Russian_Smolensk           Greece_Minoan  1.9%
200      Russian_Smolensk Germany_SouthernGermany  1.7%
201      Russian_Smolensk        Czech_CordedWare  1.3%
202      Russian_Smolensk              Poland_EBA  1.2%
203      Russian_Smolensk             Levant_Ebla    1%
204          Russian_Tver         Netherlands_MBA 59.8%
205          Russian_Tver      Germany_CordedWare  6.3%
206          Russian_Tver              Croatia_BA  1.7%
207          Russian_Tver               France_BA  1.4%
208       Russian_Voronez        Czech_CordedWare 16.1%
209       Russian_Voronez      Germany_CordedWare  6.7%
210       Russian_Voronez         Netherlands_MBA  5.3%
211       Russian_Voronez              Croatia_BA  4.4%
212       Russian_Voronez              Serbia_LBA  3.7%
213       Russian_Voronez Germany_SouthernGermany  1.9%
214       Russian_Voronez     Bulgaria_BeliBreyag  1.4%
215       Russian_Voronez              Poland_EBA  1.3%
216       Russian_Voronez             Hungary_EBA  1.3%
217       Russian_Voronez             Levant_Ebla    1%
218       Russian_Voronez      Turkey_Hellenistic    1%
219       Russian_Voronez     Kyrgyzstan_TianShan    1%
220     Russian_Yaroslavl         Netherlands_MBA 27.1%
221     Russian_Yaroslavl        Czech_CordedWare  3.9%
222     Russian_Yaroslavl              Croatia_BA  3.6%
223     Russian_Yaroslavl         Russia_Sosnoviy  2.5%
224     Russian_Yaroslavl      Germany_CordedWare    2%
225     Russian_Yaroslavl      Turkey_Hellenistic  1.9%
226     Russian_Yaroslavl          Italy_Sardinia  1.4%
227     Russian_Yaroslavl           Greece_Minoan  1.4%
228     Russian_Yaroslavl              Serbia_LBA  1.2%
229     Russian_Yaroslavl             Hungary_EBA  1.1%
230               Serbian        Czech_CordedWare  6.3%
231               Serbian             Hungary_EBA  2.8%
232               Serbian              Serbia_LBA  2.4%
233               Serbian               France_BA  2.2%
234               Serbian              Croatia_BA  2.1%
235               Serbian     Bulgaria_BeliBreyag  1.9%
236               Serbian      Turkey_Hellenistic  1.6%
237               Serbian         Croatia_Vucedol  1.6%
238               Serbian           Greece_Minoan  1.4%
239               Serbian       Croatia_Jagodnjak  1.1%
240               Serbian      Slovakia_Mikusovce    1%
241               Serbian     Portugal_Conimbriga    1%
242   Ukrainian_Chernihiv      Germany_CordedWare 15.2%
243   Ukrainian_Chernihiv         Netherlands_MBA  8.7%
244   Ukrainian_Chernihiv        Czech_CordedWare  5.8%
245   Ukrainian_Chernihiv              Croatia_BA  4.7%
246   Ukrainian_Chernihiv             Hungary_EBA  3.3%
247   Ukrainian_Chernihiv              Serbia_LBA  2.3%
248   Ukrainian_Chernihiv           Greece_Minoan  1.4%
249   Ukrainian_Chernihiv Germany_SouthernGermany  1.2%
250   Ukrainian_Chernihiv             Levant_Ebla  1.1%
251   Ukrainian_Chernihiv     Kyrgyzstan_TianShan    1%
252      Ukrainian_Dnipro        Czech_CordedWare   19%
253      Ukrainian_Dnipro         Netherlands_MBA 10.4%
254      Ukrainian_Dnipro              Croatia_BA  3.8%
255      Ukrainian_Dnipro             Hungary_EBA  2.9%
256      Ukrainian_Dnipro              Serbia_LBA  2.1%
257      Ukrainian_Dnipro      Germany_CordedWare  1.9%
258      Ukrainian_Dnipro Germany_SouthernGermany  1.2%
259      Ukrainian_Dnipro           Greece_Minoan    1%
260        Ukrainian_Lviv        Czech_CordedWare 16.2%
261        Ukrainian_Lviv              Croatia_BA  4.2%
262        Ukrainian_Lviv              Serbia_LBA  3.9%
263        Ukrainian_Lviv             Hungary_EBA  3.4%
264        Ukrainian_Lviv           Greece_Minoan    2%
265        Ukrainian_Lviv      Germany_CordedWare  1.5%
266        Ukrainian_Lviv             Germany_EBA  1.4%
267        Ukrainian_Lviv        France_Occitanie  1.2%
268        Ukrainian_Lviv               France_BA  1.2%
269        Ukrainian_Lviv Germany_SouthernGermany    1%
270       Ukrainian_Rivne        Czech_CordedWare 16.7%
271       Ukrainian_Rivne      Germany_CordedWare 11.6%
272       Ukrainian_Rivne         Netherlands_MBA  9.9%
273       Ukrainian_Rivne              Croatia_BA  3.7%
274       Ukrainian_Rivne             Hungary_EBA  2.9%
275       Ukrainian_Rivne              Serbia_LBA  1.8%
276       Ukrainian_Rivne           Greece_Minoan  1.5%
277        Ukrainian_Sumy         Netherlands_MBA  8.7%
278        Ukrainian_Sumy              Croatia_BA  5.1%
279        Ukrainian_Sumy              Serbia_LBA  3.8%
280        Ukrainian_Sumy             Hungary_EBA  3.2%
281        Ukrainian_Sumy      Germany_CordedWare  2.7%
282        Ukrainian_Sumy Germany_SouthernGermany  1.9%
283        Ukrainian_Sumy              Syria_Ebla  1.5%
284        Ukrainian_Sumy        Czech_CordedWare  1.5%
285        Ukrainian_Sumy           Greece_Minoan  1.3%
286        Ukrainian_Sumy              Poland_EBA  1.2%
287        Ukrainian_Sumy             Levant_Ebla  1.2%
288        Ukrainian_Sumy      Turkey_Hellenistic  1.1%
289 Ukrainian_Zakarpattia        Czech_CordedWare 88.8%
290    Ukrainian_Zhytomyr        Czech_CordedWare 18.1%
291    Ukrainian_Zhytomyr              Croatia_BA  4.2%
292    Ukrainian_Zhytomyr         Netherlands_MBA  3.5%
293    Ukrainian_Zhytomyr             Hungary_EBA  3.4%
294    Ukrainian_Zhytomyr      Germany_CordedWare  1.9%
295    Ukrainian_Zhytomyr              Serbia_LBA  1.7%
296    Ukrainian_Zhytomyr           Greece_Minoan  1.6%
297    Ukrainian_Zhytomyr Germany_SouthernGermany  1.3%
298    Ukrainian_Zhytomyr              Poland_EBA  1.2%
299    Ukrainian_Zhytomyr             Levant_Ebla    1%
300  Ukrainian_Zhytomyr_o     Bulgaria_BeliBreyag  3.4%
301  Ukrainian_Zhytomyr_o             Lebanon_MBA  1.7%
302  Ukrainian_Zhytomyr_o             Hungary_MBA  1.7%
303  Ukrainian_Zhytomyr_o             Armenia_MBA  1.5%
304  Ukrainian_Zhytomyr_o        Armenia_Lchashen  1.4%
305  Ukrainian_Zhytomyr_o      Slovakia_Mikusovce  1.3%
306  Ukrainian_Zhytomyr_o Ukraine_GlobularAmphora  1.2%
307  Ukrainian_Zhytomyr_o            Iran_Hasanlu  1.1%

options(repr.plot.width = 12, repr.plot.height = 12, repr.plot.res = 400)

plotfun(mprd %>% sample_n(16),lsz = 2,nrw = 4)

mdl = myfun(na.omit(iad),e = 0.5,a = 1,l = 10)

[1] "Number of classes: 129"
[1] "Split into test and train samples"
[1] 591  26
[1] 197  26
[1] "Starting XGBoost training"
[1]	train-mlogloss:4.496463	test-mlogloss:4.464959 
[26]	train-mlogloss:2.439974	test-mlogloss:2.992633 
[51]	train-mlogloss:1.889101	test-mlogloss:2.780811 
[76]	train-mlogloss:1.621736	test-mlogloss:2.710373 
[100]	train-mlogloss:1.464849	test-mlogloss:2.673704 
# A tibble: 15 × 5
     row label variable value maxval
   <int> <dbl> <chr>    <dbl>  <dbl>
 1    94    26 26       0.933  0.933
 2    73    26 26       0.614  0.614
 3    46    23 26       0.596  0.596
 4   125    49 58       0.273  0.273
 5   158    88 88       0.333  0.333
 6   196   127 107      0.249  0.249
 7   150    76 76       0.824  0.824
 8   162    92 92       0.503  0.503
 9    99    30 14       0.116  0.116
10   105    35 107      0.424  0.424
11   183   117 17       0.101  0.101
12   181   110 44       0.189  0.189
13    12     7 7        0.803  0.803
14    85    26 26       0.928  0.928
15    63    26 26       0.756  0.756
[1] "test-error = 0.543147208121827"

mprd = mypfun(mdl,iad,ppl)

[1] "Using 129 populations"

Joining with `by = join_by(variable)`

   name                   eth  value
1    MD        Italy_Sardinia  6.01%
2    MD          Iran_Hasanlu  2.48%
3    MD         Greece_Delphi  2.16%
4    MN  France_LesMarmousets     4%
5    MN          Iran_Hasanlu   2.8%
6    MN        Italy_Sardinia   2.4%
7    MN    ChannelIslands_EIA  2.19%
8    MN           Slovakia_IA  2.02%
9    RN        Italy_Sardinia  3.99%
10   RN  France_LesMarmousets  2.93%
11   RN Slovakia_BytcaHrabove  2.88%
12   RN          Iran_Hasanlu  2.47%
13   TP           Hungary_EIA  9.03%
14   TP      Poland_Kowalewko   8.7%
15   TP           Croatia_LIA  6.21%
16   TP             Norway_IA  4.96%
17   TP          Poland_Gaski  3.69%
18   TP      Poland_Maslomecz  2.69%
19   TP Slovakia_BytcaHrabove 12.26%

mprd = mypfun2(mdl,iad,ppl)

[1] "Using 129 populations"

Joining with `by = join_by(variable)`

[1] "Using 129 populations"

Joining with `by = join_by(variable)`

[1] "Using 129 populations"

Joining with `by = join_by(variable)`

[1] "Using 129 populations"

Joining with `by = join_by(variable)`

[1] "Using 129 populations"

Joining with `by = join_by(variable)`

plotfun3(mprd)

Warning message:
“ggrepel: 7 unlabeled data points (too many overlaps). Consider increasing max.overlaps”

mprd = mypfun(mdl,iad,smpls)

[1] "Using 124 populations"

Joining with `by = join_by(variable)`

                     name                           eth value
1    Ashkenazi_Belarussia                   Armenia_LBA  1.4%
2    Ashkenazi_Belarussia                 Italy_Tuscany  1.4%
3    Ashkenazi_Belarussia                  Iran_Hasanlu  1.4%
4    Ashkenazi_Belarussia                   Slovakia_IA  1.3%
5    Ashkenazi_Belarussia          France_LesMarmousets  1.3%
6    Ashkenazi_Belarussia                   Italy_Lazio  1.2%
7    Ashkenazi_Belarussia           Kyrgyzstan_TianShan  1.1%
8    Ashkenazi_Belarussia             Moldova_Cimmerian  1.1%
9    Ashkenazi_Belarussia              Kazakstan_Sargat  1.1%
10   Ashkenazi_Belarussia                     Spain_EIA  1.1%
11   Ashkenazi_Belarussia                     Israel_IA    1%
12   Ashkenazi_Belarussia               Iran_HajjiFiruz    1%
13   Ashkenazi_Belarussia                 Montenegro_IA    1%
14   Ashkenazi_Belarussia                  Scotland_MIA    1%
15   Ashkenazi_Belarussia                  Mongolia_Uvs    1%
16   Ashkenazi_Belarussia               Kazakhstan_Turk    1%
17    Ashkenazi_Lithuania                   Slovakia_IA  1.7%
18    Ashkenazi_Lithuania          France_LesMarmousets  1.5%
19    Ashkenazi_Lithuania                   Armenia_LBA  1.4%
20    Ashkenazi_Lithuania               Iran_HajjiFiruz  1.3%
21    Ashkenazi_Lithuania                 Italy_Tuscany  1.3%
22    Ashkenazi_Lithuania                   Hungary_EIA  1.3%
23    Ashkenazi_Lithuania                  Iran_Hasanlu  1.3%
24    Ashkenazi_Lithuania                   Italy_Lazio  1.1%
25    Ashkenazi_Lithuania                  Mongolia_Uvs  1.1%
26    Ashkenazi_Lithuania        Armenia_UrartianEmpire  1.1%
27    Ashkenazi_Lithuania           Kyrgyzstan_TianShan  1.1%
28    Ashkenazi_Lithuania              Kazakstan_Sargat  1.1%
29    Ashkenazi_Lithuania                     Israel_IA    1%
30    Ashkenazi_Lithuania             Moldova_Cimmerian    1%
31    Ashkenazi_Lithuania                     Spain_EIA    1%
32    Ashkenazi_Lithuania                  Scotland_MIA    1%
33    Ashkenazi_Lithuania               Kazakhstan_Turk    1%
34      Ashkenazi_Ukraine          France_LesMarmousets  3.8%
35      Ashkenazi_Ukraine                   Slovakia_IA  1.8%
36      Ashkenazi_Ukraine                 Italy_Tuscany  1.3%
37      Ashkenazi_Ukraine                  Iran_Hasanlu  1.3%
38      Ashkenazi_Ukraine                   Italy_Lazio  1.2%
39      Ashkenazi_Ukraine            ChannelIslands_EIA  1.1%
40      Ashkenazi_Ukraine         Slovakia_BytcaHrabove  1.1%
41      Ashkenazi_Ukraine           Kyrgyzstan_TianShan  1.1%
42      Ashkenazi_Ukraine              Kazakstan_Sargat  1.1%
43      Ashkenazi_Ukraine                     Israel_IA    1%
44      Ashkenazi_Ukraine            Turkey_Hellenistic    1%
45      Ashkenazi_Ukraine                     Spain_EIA    1%
46      Ashkenazi_Ukraine        Armenia_UrartianEmpire    1%
47      Ashkenazi_Ukraine                Italy_Sardinia    1%
48      Ashkenazi_Ukraine                  Scotland_MIA    1%
49      Ashkenazi_Ukraine             Moldova_Cimmerian    1%
50             Belarusian         Slovakia_BytcaHrabove 45.3%
51             Belarusian                   Hungary_EIA 14.9%
52             Belarusian                   Nordland_IA  3.2%
53             Belarusian                     Norway_IA  1.6%
54             Belarusian            Slovakia_Mikusovce    1%
55                Bosnian                   Hungary_EIA 35.6%
56                Bosnian         Slovakia_BytcaHrabove 22.9%
57                Bosnian                   England_LIA  1.3%
58                Bosnian                   Croatia_LIA  1.2%
59      Cossack_Ukrainian         Slovakia_BytcaHrabove 36.2%
60      Cossack_Ukrainian                   Hungary_EIA 15.8%
61      Cossack_Ukrainian                   Croatia_LIA  2.4%
62      Cossack_Ukrainian                     Norway_IA  1.7%
63      Cossack_Ukrainian           Macedonia_Classical  1.6%
64      Cossack_Ukrainian                   Nordland_IA  1.4%
65      Cossack_Ukrainian            Slovakia_Mikusovce  1.2%
66               Croatian                   Hungary_EIA 33.1%
67               Croatian         Slovakia_BytcaHrabove 27.1%
68               Croatian                   Croatia_LIA  2.8%
69                  Czech         Slovakia_BytcaHrabove 19.2%
70                  Czech                   Hungary_EIA 16.9%
71                  Czech                   Croatia_LIA  5.3%
72                  Czech                   England_LIA  1.2%
73                  Czech                     Norway_IA  1.1%
74                  Czech Egypt_ThirdIntermediatePeriod  1.1%
75               Estonian                   Hungary_EIA 15.8%
76               Estonian         Slovakia_BytcaHrabove 12.4%
77               Estonian                   Nordland_IA  8.1%
78               Estonian                     Norway_IA    3%
79               Estonian                   Croatia_LIA  1.8%
80               Estonian              Kazakhstan_Nomad  1.6%
81               Estonian            Slovakia_Mikusovce  1.4%
82               Estonian                   England_EIA  1.2%
83               Estonian          Sudan_EarlyChristian  1.2%
84               Estonian                 Russia_Samara  1.2%
85               Estonian                   England_LIA  1.1%
86               Estonian                 Greece_Delphi    1%
87               Estonian              Kazakstan_Sargat    1%
88                Ingrian         Slovakia_BytcaHrabove   15%
89                Ingrian                   Nordland_IA  5.3%
90                Ingrian                   Hungary_EIA  5.1%
91                Ingrian                     Norway_IA  2.9%
92                Ingrian                  Scotland_EIA  1.8%
93                Ingrian              Kazakhstan_Nomad  1.5%
94                Ingrian                 Russia_Samara  1.5%
95                Ingrian Egypt_ThirdIntermediatePeriod  1.5%
96                Ingrian                   Croatia_LIA  1.4%
97                Ingrian          Sudan_EarlyChristian  1.4%
98                Ingrian              Kazakstan_Sargat  1.2%
99                Ingrian                   England_LIA  1.1%
100               Ingrian                    England_IA    1%
101               Ingrian                   Slovakia_IA    1%
102              Karelian         Slovakia_BytcaHrabove  9.5%
103              Karelian                   Nordland_IA  7.4%
104              Karelian                   Hungary_EIA  4.6%
105              Karelian                     Norway_IA    3%
106              Karelian              Kazakhstan_Nomad  2.1%
107              Karelian                  Scotland_EIA  1.9%
108              Karelian          Sudan_EarlyChristian  1.5%
109              Karelian                 Russia_Samara  1.4%
110              Karelian              Kazakstan_Sargat  1.4%
111              Karelian Egypt_ThirdIntermediatePeriod  1.3%
112              Karelian                    England_IA  1.1%
113              Karelian                   Slovakia_IA  1.1%
114              Karelian           Kazakhstan_Kipchak2  1.1%
115              Karelian                     Czech_LBA  1.1%
116                   Lak                    Armenia_IA 33.8%
117                   Lak                   Armenia_LBA  6.8%
118                   Lak                   Armenia_EIA  3.3%
119                   Lak                 Russia_Samara  2.6%
120                   Lak              Armenia_Beniamin    2%
121                   Lak            Armenia_Achaemenid  1.8%
122                   Lak              Kazakstan_Sargat  1.3%
123                   Lak          France_LesMarmousets  1.1%
124               Latvian                   Hungary_EIA   28%
125               Latvian         Slovakia_BytcaHrabove 17.2%
126               Latvian                   Nordland_IA  5.7%
127               Latvian                     Norway_IA  2.4%
128               Latvian                   England_EIA  1.8%
129               Latvian                   Croatia_LIA  1.1%
130               Latvian            Slovakia_Mikusovce    1%
131         Lithuanian_PA                   Hungary_EIA 29.2%
132         Lithuanian_PA         Slovakia_BytcaHrabove 28.1%
133         Lithuanian_PA                   Nordland_IA  4.3%
134         Lithuanian_PA                     Norway_IA  1.8%
135         Lithuanian_PA                   Croatia_LIA  1.6%
136         Lithuanian_PA              Kazakhstan_Nomad    1%
137         Lithuanian_PA                   England_EIA    1%
138         Lithuanian_PZ         Slovakia_BytcaHrabove 26.1%
139         Lithuanian_PZ                   Hungary_EIA   15%
140         Lithuanian_PZ                   Nordland_IA  5.8%
141         Lithuanian_PZ                   England_EIA  3.3%
142         Lithuanian_PZ                     Norway_IA  2.5%
143         Lithuanian_PZ            Slovakia_Mikusovce  1.9%
144         Lithuanian_PZ                   Croatia_LIA  1.2%
145         Lithuanian_PZ              Kazakhstan_Nomad    1%
146         Lithuanian_RA         Slovakia_BytcaHrabove 44.2%
147         Lithuanian_RA                   Hungary_EIA 24.5%
148         Lithuanian_RA                   Nordland_IA  3.2%
149         Lithuanian_RA                     Norway_IA  1.4%
150         Lithuanian_RA                   Croatia_LIA  1.3%
151         Lithuanian_SZ                   Hungary_EIA 28.1%
152         Lithuanian_SZ         Slovakia_BytcaHrabove 23.5%
153         Lithuanian_SZ                   Nordland_IA  5.2%
154         Lithuanian_SZ                     Norway_IA    2%
155         Lithuanian_SZ                   England_EIA  1.1%
156         Lithuanian_SZ              Kazakhstan_Nomad    1%
157         Lithuanian_VA                   Hungary_EIA 31.9%
158         Lithuanian_VA         Slovakia_BytcaHrabove 21.9%
159         Lithuanian_VA                   Nordland_IA  4.6%
160         Lithuanian_VA                     Norway_IA  2.1%
161         Lithuanian_VA                   Croatia_LIA  1.5%
162         Lithuanian_VA                   England_EIA  1.1%
163         Lithuanian_VZ                   Hungary_EIA 28.5%
164         Lithuanian_VZ         Slovakia_BytcaHrabove 23.3%
165         Lithuanian_VZ                   Nordland_IA  4.8%
166         Lithuanian_VZ                     Norway_IA    2%
167         Lithuanian_VZ                   England_EIA  1.2%
168         Lithuanian_VZ                   Croatia_LIA  1.1%
169         Lithuanian_VZ            Slovakia_Mikusovce    1%
170        North_Ossetian                    Armenia_IA 87.9%
171        North_Ossetian              Armenia_Beniamin  2.4%
172              Ossetian                    Armenia_IA 84.8%
173              Ossetian              Armenia_Beniamin  2.6%
174              Ossetian            Armenia_Achaemenid  1.6%
175                Polish                   Hungary_EIA 25.6%
176                Polish         Slovakia_BytcaHrabove 22.4%
177                Polish                   Nordland_IA    2%
178                Polish                   England_EIA    2%
179                Polish                     Norway_IA  1.7%
180                Polish                   Croatia_LIA  1.4%
181      Polish_Kashubian         Slovakia_BytcaHrabove 26.1%
182      Polish_Kashubian                   Hungary_EIA 18.5%
183      Polish_Kashubian                   Nordland_IA  5.6%
184      Polish_Kashubian                     Norway_IA  2.2%
185      Polish_Kashubian                  Scotland_EIA  2.1%
186      Polish_Kashubian                   Croatia_LIA  1.6%
187      Polish_Kashubian                   England_EIA  1.5%
188      Polish_Kashubian          Sudan_EarlyChristian  1.2%
189      Polish_Kashubian                Italy_Sardinia  1.1%
190      Polish_Kashubian                 Greece_Delphi  1.1%
191       Polish_Silesian                   Hungary_EIA 36.6%
192       Polish_Silesian         Slovakia_BytcaHrabove   11%
193       Polish_Silesian          Sudan_EarlyChristian  1.3%
194       Polish_Silesian                     Norway_IA  1.2%
195       Polish_Silesian                   Nordland_IA  1.1%
196      Russian_Belgorod         Slovakia_BytcaHrabove   39%
197      Russian_Belgorod                   Hungary_EIA 22.7%
198        Russian_Kaluga         Slovakia_BytcaHrabove 21.9%
199        Russian_Kaluga                   Hungary_EIA  7.3%
200        Russian_Kaluga                   Nordland_IA  4.9%
201        Russian_Kaluga                     Norway_IA  2.6%
202        Russian_Kaluga            Slovakia_Mikusovce  1.6%
203        Russian_Kaluga                  Scotland_EIA  1.4%
204        Russian_Kaluga          Sudan_EarlyChristian  1.3%
205        Russian_Kaluga                   England_EIA  1.1%
206        Russian_Kaluga              Kazakstan_Sargat  1.1%
207        Russian_Kaluga                   Croatia_LIA    1%
208        Russian_Kaluga                 Greece_Delphi    1%
209      Russian_Kostroma                   Hungary_EIA 18.8%
210      Russian_Kostroma         Slovakia_BytcaHrabove 15.1%
211      Russian_Kostroma                   Nordland_IA  4.3%
212      Russian_Kostroma                     Norway_IA  2.2%
213      Russian_Kostroma              Kazakstan_Sargat  1.2%
214      Russian_Kostroma          Sudan_EarlyChristian  1.2%
215      Russian_Kostroma                 Russia_Samara  1.1%
216  Russian_Krasnoborsky         Slovakia_BytcaHrabove 14.4%
217  Russian_Krasnoborsky                   Hungary_EIA  8.6%
218  Russian_Krasnoborsky                   Nordland_IA    5%
219  Russian_Krasnoborsky                     Norway_IA  2.7%
220  Russian_Krasnoborsky              Kazakhstan_Nomad  1.5%
221  Russian_Krasnoborsky              Kazakstan_Sargat  1.4%
222  Russian_Krasnoborsky          Sudan_EarlyChristian  1.4%
223  Russian_Krasnoborsky                 Russia_Samara  1.3%
224  Russian_Krasnoborsky                   Croatia_LIA  1.1%
225  Russian_Krasnoborsky                     Czech_LBA    1%
226  Russian_Krasnoborsky                  Scotland_EIA    1%
227  Russian_Krasnoborsky                 Greece_Delphi    1%
228         Russian_Kursk                   Hungary_EIA 30.8%
229         Russian_Kursk         Slovakia_BytcaHrabove   26%
230         Russian_Kursk                   Nordland_IA  2.2%
231         Russian_Kursk                     Norway_IA  1.5%
232         Russian_Kursk                   Croatia_LIA  1.5%
233   Russian_Leshukonsky                   Nordland_IA  5.7%
234   Russian_Leshukonsky                 Russia_Samara  3.6%
235   Russian_Leshukonsky                   Hungary_EIA  3.4%
236   Russian_Leshukonsky                     Norway_IA    3%
237   Russian_Leshukonsky              Kazakhstan_Nomad  2.4%
238   Russian_Leshukonsky                    Romback_IA    2%
239   Russian_Leshukonsky           Kazakhstan_Kipchak2  1.9%
240   Russian_Leshukonsky         Slovakia_BytcaHrabove  1.7%
241   Russian_Leshukonsky              Kazakstan_Sargat  1.7%
242   Russian_Leshukonsky          Sudan_EarlyChristian  1.6%
243   Russian_Leshukonsky                    England_IA  1.3%
244   Russian_Leshukonsky            Armenia_Achaemenid  1.2%
245   Russian_Leshukonsky                  Macedonia_IA  1.2%
246   Russian_Leshukonsky                     Czech_LBA  1.2%
247   Russian_Leshukonsky                    Syria_Ebla    1%
248          Russian_Orel         Slovakia_BytcaHrabove 35.7%
249          Russian_Orel                   Hungary_EIA 24.1%
250          Russian_Orel                     Norway_IA  1.4%
251          Russian_Orel                   Nordland_IA  1.3%
252        Russian_Pinega         Slovakia_BytcaHrabove   10%
253        Russian_Pinega                   Nordland_IA  7.5%
254        Russian_Pinega                   Hungary_EIA  6.3%
255        Russian_Pinega                 Russia_Samara  2.8%
256        Russian_Pinega                     Norway_IA  2.7%
257        Russian_Pinega                  Scotland_EIA    2%
258        Russian_Pinega              Kazakhstan_Nomad  1.9%
259        Russian_Pinega          Sudan_EarlyChristian  1.5%
260        Russian_Pinega              Kazakstan_Sargat  1.4%
261        Russian_Pinega           Kazakhstan_Kipchak2  1.3%
262        Russian_Pinega                 Greece_Delphi  1.1%
263        Russian_Pinega                   Slovakia_IA  1.1%
264        Russian_Pinega                    England_IA    1%
265     Russian_Pinezhsky                   Nordland_IA  7.8%
266     Russian_Pinezhsky              Kazakhstan_Nomad  5.2%
267     Russian_Pinezhsky                   Hungary_EIA  4.8%
268     Russian_Pinezhsky         Slovakia_BytcaHrabove    4%
269     Russian_Pinezhsky                     Norway_IA    3%
270     Russian_Pinezhsky                 Russia_Samara  2.5%
271     Russian_Pinezhsky                  Scotland_EIA  1.9%
272     Russian_Pinezhsky          Sudan_EarlyChristian  1.5%
273     Russian_Pinezhsky              Kazakstan_Sargat  1.3%
274     Russian_Pinezhsky                    England_IA  1.2%
275     Russian_Pinezhsky                 Greece_Delphi  1.2%
276     Russian_Pinezhsky                   Slovakia_IA  1.1%
277     Russian_Pinezhsky           Kazakhstan_Kipchak2  1.1%
278     Russian_Pinezhsky                     Czech_LBA  1.1%
279     Russian_Pinezhsky             Moldova_Cimmerian  1.1%
280         Russian_Pskov         Slovakia_BytcaHrabove 27.2%
281         Russian_Pskov                   Hungary_EIA 25.4%
282         Russian_Pskov                   Nordland_IA  3.4%
283         Russian_Pskov                     Norway_IA  1.8%
284        Russian_Ryazan                   Hungary_EIA   23%
285        Russian_Ryazan         Slovakia_BytcaHrabove 18.7%
286        Russian_Ryazan                   Nordland_IA  3.1%
287        Russian_Ryazan                     Norway_IA  1.6%
288        Russian_Ryazan                   Croatia_LIA  1.5%
289        Russian_Ryazan                  Scotland_EIA  1.1%
290        Russian_Ryazan          Sudan_EarlyChristian  1.1%
291        Russian_Ryazan              Kazakstan_Sargat  1.1%
292      Russian_Smolensk         Slovakia_BytcaHrabove 31.7%
293      Russian_Smolensk                   Hungary_EIA 13.9%
294      Russian_Smolensk                   Nordland_IA  3.2%
295      Russian_Smolensk                     Norway_IA    2%
296      Russian_Smolensk                   England_EIA  1.7%
297      Russian_Smolensk                 Greece_Delphi  1.3%
298      Russian_Smolensk            Slovakia_Mikusovce    1%
299          Russian_Tver                   Hungary_EIA 47.8%
300          Russian_Tver         Slovakia_BytcaHrabove 13.6%
301          Russian_Tver                   Nordland_IA  2.5%
302          Russian_Tver                     Norway_IA  1.3%
303       Russian_Voronez         Slovakia_BytcaHrabove 25.9%
304       Russian_Voronez                   Hungary_EIA 20.3%
305       Russian_Voronez                     Norway_IA    2%
306       Russian_Voronez                   Nordland_IA  1.9%
307       Russian_Voronez            Slovakia_Mikusovce  1.6%
308       Russian_Voronez                   Croatia_LIA  1.1%
309       Russian_Voronez          Sudan_EarlyChristian    1%
310     Russian_Yaroslavl                   Hungary_EIA 17.5%
311     Russian_Yaroslavl         Slovakia_BytcaHrabove 15.7%
312     Russian_Yaroslavl                   Nordland_IA  3.8%
313     Russian_Yaroslavl                     Norway_IA  2.3%
314     Russian_Yaroslavl                   Croatia_LIA  1.9%
315     Russian_Yaroslavl              Kazakhstan_Nomad  1.8%
316     Russian_Yaroslavl              Kazakstan_Sargat  1.3%
317     Russian_Yaroslavl          Sudan_EarlyChristian  1.2%
318     Russian_Yaroslavl                 Russia_Samara    1%
319               Serbian                   Hungary_EIA 40.6%
320               Serbian         Slovakia_BytcaHrabove 24.9%
321               Serbian            ChannelIslands_EIA  2.4%
322   Ukrainian_Chernihiv         Slovakia_BytcaHrabove 34.4%
323   Ukrainian_Chernihiv                   Hungary_EIA   25%
324   Ukrainian_Chernihiv                   Croatia_LIA  1.4%
325   Ukrainian_Chernihiv                   Nordland_IA  1.4%
326   Ukrainian_Chernihiv                     Norway_IA  1.3%
327      Ukrainian_Dnipro                   Hungary_EIA 28.2%
328      Ukrainian_Dnipro         Slovakia_BytcaHrabove 25.4%
329      Ukrainian_Dnipro                   Nordland_IA  1.4%
330      Ukrainian_Dnipro                   Croatia_LIA  1.3%
331      Ukrainian_Dnipro                     Norway_IA  1.2%
332        Ukrainian_Lviv         Slovakia_BytcaHrabove 35.5%
333        Ukrainian_Lviv                   Hungary_EIA 22.4%
334        Ukrainian_Lviv                   Croatia_LIA  1.5%
335       Ukrainian_Rivne         Slovakia_BytcaHrabove 34.4%
336       Ukrainian_Rivne                   Hungary_EIA 24.3%
337       Ukrainian_Rivne                   Nordland_IA  2.1%
338       Ukrainian_Rivne                     Norway_IA  1.2%
339       Ukrainian_Rivne                   Croatia_LIA  1.1%
340        Ukrainian_Sumy         Slovakia_BytcaHrabove 32.2%
341        Ukrainian_Sumy                   Hungary_EIA 16.7%
342        Ukrainian_Sumy                   Croatia_LIA  1.5%
343        Ukrainian_Sumy                   Nordland_IA  1.5%
344        Ukrainian_Sumy                     Norway_IA  1.5%
345 Ukrainian_Zakarpattia                   Hungary_EIA   28%
346 Ukrainian_Zakarpattia         Slovakia_BytcaHrabove 23.4%
347 Ukrainian_Zakarpattia                   Croatia_LIA    2%
348    Ukrainian_Zhytomyr         Slovakia_BytcaHrabove 32.5%
349    Ukrainian_Zhytomyr                   Hungary_EIA   14%
350    Ukrainian_Zhytomyr                     Norway_IA  1.9%
351    Ukrainian_Zhytomyr                   Nordland_IA  1.8%
352    Ukrainian_Zhytomyr                  Scotland_EIA    1%
353  Ukrainian_Zhytomyr_o          France_LesMarmousets  3.3%
354  Ukrainian_Zhytomyr_o         Slovakia_BytcaHrabove  2.1%
355  Ukrainian_Zhytomyr_o                   Slovakia_IA  1.6%
356  Ukrainian_Zhytomyr_o                   Hungary_EIA  1.6%
357  Ukrainian_Zhytomyr_o            ChannelIslands_EIA  1.4%
358  Ukrainian_Zhytomyr_o                   Armenia_LBA  1.4%
359  Ukrainian_Zhytomyr_o             Moldova_Cimmerian  1.3%
360  Ukrainian_Zhytomyr_o                  Iran_Hasanlu  1.3%
361  Ukrainian_Zhytomyr_o                 Italy_Tuscany  1.3%
362  Ukrainian_Zhytomyr_o           Kyrgyzstan_TianShan  1.1%
363  Ukrainian_Zhytomyr_o              Kazakstan_Sargat  1.1%
364  Ukrainian_Zhytomyr_o                   Italy_Lazio  1.1%
365  Ukrainian_Zhytomyr_o            Armenia_Achaemenid  1.1%
366  Ukrainian_Zhytomyr_o         England_EastYorkshire  1.1%
367  Ukrainian_Zhytomyr_o                    Syria_Ebla  1.1%
368  Ukrainian_Zhytomyr_o                     Spain_EIA    1%

options(repr.plot.width = 12, repr.plot.height = 12, repr.plot.res = 400)

plotfun(mprd %>% sample_n(16),lsz = 2,nrw = 4)

mdl = myfun(na.omit(mad),e = 1,a = 0,l = 15)

[1] "Number of classes: 131"
[1] "Split into test and train samples"
[1] 727  26
[1] 243  26
[1] "Starting XGBoost training"
[1]	train-mlogloss:4.236831	test-mlogloss:4.322459 
[26]	train-mlogloss:1.628838	test-mlogloss:3.342472 
[51]	train-mlogloss:1.043319	test-mlogloss:3.344535 
[76]	train-mlogloss:0.791594	test-mlogloss:3.397657 
[100]	train-mlogloss:0.663981	test-mlogloss:3.449302 
# A tibble: 15 × 5
     row label variable  value maxval
   <int> <dbl> <chr>     <dbl>  <dbl>
 1   192   110 119      0.156  0.156 
 2   125    57 57       0.0836 0.0836
 3   123    57 65       0.235  0.235 
 4    91    30 14       0.833  0.833 
 5   229   119 119      0.386  0.386 
 6    63    17 119      0.327  0.327 
 7   181   104 17       0.512  0.512 
 8   170    85 119      0.289  0.289 
 9   207   119 30       0.240  0.240 
10    12    11 74       0.159  0.159 
11   166    85 119      0.310  0.310 
12    41    14 14       0.988  0.988 
13   160    83 119      0.487  0.487 
14   155    75 13       0.0882 0.0882
15   180   102 130      0.969  0.969 
[1] "test-error = 0.748971193415638"

mprd = mypfun(mdl,mad,ppl)

[1] "Using 131 populations"

Joining with `by = join_by(variable)`

   name                       eth  value
1    MD Turkey_SoutheastByzantine  4.16%
2    MD           Turkey_Medieval  3.72%
3    MD         Syria_TellMasaikh  3.29%
4    MD          Portugal_Miroico  2.07%
5    MD               Italy_Lazio  10.6%
6    MN               Italy_Lazio 69.69%
7    RN               Italy_Lazio  59.3%
8    RN Turkey_SoutheastByzantine  2.44%
9    TP        Sweden_EarlyViking  8.12%
10   TP            Poland_Konskie 30.76%
11   TP           Poland_Balczewo  3.35%
12   TP            Denmark_Viking  2.41%
13   TP       Poland_Dziekanowice  2.21%

mprd = mypfun2(mdl,mad,ppl)

[1] "Using 131 populations"

Joining with `by = join_by(variable)`

[1] "Using 131 populations"

Joining with `by = join_by(variable)`

[1] "Using 131 populations"

Joining with `by = join_by(variable)`

[1] "Using 131 populations"

Joining with `by = join_by(variable)`

[1] "Using 131 populations"

Joining with `by = join_by(variable)`

plotfun3(mprd)

Warning message:
“ggrepel: 6 unlabeled data points (too many overlaps). Consider increasing max.overlaps”

mprd = mypfun(mdl,mad,smpls)

[1] "Using 163 populations"

Joining with `by = join_by(variable)`

                     name                           eth value
1    Ashkenazi_Belarussia                   Italy_Lazio 66.9%
2     Ashkenazi_Lithuania                   Italy_Lazio 51.7%
3     Ashkenazi_Lithuania               Kyrgyzstan_Saka  1.6%
4     Ashkenazi_Lithuania               Israel_Medieval  1.5%
5     Ashkenazi_Lithuania              Portugal_Miroico  1.1%
6     Ashkenazi_Lithuania    BosniaHerzegovina_Medieval    1%
7       Ashkenazi_Ukraine                   Italy_Lazio 51.2%
8       Ashkenazi_Ukraine               Kyrgyzstan_Saka  1.7%
9              Belarusian                Poland_Konskie    7%
10             Belarusian                 Poland_Milicz  6.4%
11             Belarusian            Sweden_EarlyViking  5.3%
12             Belarusian                Poland_Niemcza  3.6%
13             Belarusian                    Poland_Lad  3.3%
14             Belarusian             Poland_Oblaczkowo  3.3%
15             Belarusian               Poland_Balczewo  2.9%
16             Belarusian              Russia_UstBelaya  2.8%
17             Belarusian          Mongolia_Uvurkhangai  2.6%
18             Belarusian           Poland_Dziekanowice  2.4%
19             Belarusian                 Poland_Ostrow    2%
20             Belarusian             Germany_EMedieval  1.6%
21             Belarusian                   Jamtland_VA  1.3%
22             Belarusian                Serbia_Naissus  1.2%
23             Belarusian                 Croatia_Sipar  1.2%
24             Belarusian                 Poland_Legowo  1.1%
25             Belarusian              Ukraine_Medieval  1.1%
26             Belarusian                  Poland_Rumin  1.1%
27                Bosnian            Sweden_EarlyViking  8.8%
28                Bosnian          Mongolia_Uvurkhangai  4.7%
29                Bosnian                Serbia_Naissus    3%
30                Bosnian    BosniaHerzegovina_Medieval  2.2%
31                Bosnian           Poland_Dziekanowice  2.1%
32                Bosnian               Slovakia_Poprad  1.9%
33                Bosnian           Denmark_EarlyViking  1.7%
34                Bosnian                 China_Guangxi  1.6%
35                Bosnian                   Italy_Lazio  1.5%
36                Bosnian               Poland_Balczewo  1.3%
37                Bosnian       Slovakia_TesarkeMlynany  1.2%
38      Cossack_Ukrainian              Russia_UstBelaya 16.1%
39      Cossack_Ukrainian                Poland_Konskie  5.6%
40      Cossack_Ukrainian                  Uppsala_Late  4.1%
41      Cossack_Ukrainian                   Jamtland_VA    3%
42      Cossack_Ukrainian                 Poland_Ostrow  2.7%
43      Cossack_Ukrainian                Poland_Niemcza  2.1%
44      Cossack_Ukrainian               Poland_Balczewo    2%
45      Cossack_Ukrainian                Italy_Sardinia    2%
46      Cossack_Ukrainian                    Poland_Lad  1.6%
47      Cossack_Ukrainian           Poland_Dziekanowice  1.5%
48      Cossack_Ukrainian                 Poland_Milicz  1.4%
49      Cossack_Ukrainian                Serbia_Sirmium  1.2%
50      Cossack_Ukrainian           Mongolia_Sukhbaatar  1.1%
51      Cossack_Ukrainian          Mongolia_Uvurkhangai  1.1%
52      Cossack_Ukrainian            Sweden_EarlyViking  1.1%
53               Croatian            Sweden_EarlyViking 10.9%
54               Croatian                   Italy_Lazio  5.5%
55               Croatian                Serbia_Naissus  2.3%
56               Croatian           Poland_Dziekanowice  1.8%
57               Croatian    BosniaHerzegovina_Medieval  1.6%
58               Croatian               Poland_Balczewo  1.2%
59               Croatian                 Norway_Viking  1.1%
60               Croatian           Denmark_EarlyViking  1.1%
61               Croatian                Poland_Niemcza    1%
62                  Czech           Denmark_EarlyViking  5.7%
63                  Czech                Poland_Konskie  5.1%
64                  Czech            Sweden_EarlyViking  4.9%
65                  Czech              Russia_UstBelaya    4%
66                  Czech                Serbia_Naissus  1.8%
67                  Czech                 Poland_Ostrow  1.7%
68                  Czech                 Croatia_Sipar  1.6%
69                  Czech    BosniaHerzegovina_Medieval  1.2%
70                  Czech           Poland_Dziekanowice  1.1%
71                  Czech                  Mongolia_LBA  1.1%
72               Estonian            Sweden_EarlyViking   61%
73               Estonian                  Uppsala_Late    5%
74               Estonian              Russia_UstBelaya  1.4%
75               Estonian                Spain_Visigoth  1.3%
76               Estonian               Poland_Balczewo  1.3%
77               Estonian           Poland_Dziekanowice  1.2%
78                Ingrian                  Uppsala_Late 36.7%
79                Ingrian            Sweden_EarlyViking 14.1%
80                Ingrian              Russia_UstBelaya  5.5%
81                Ingrian                   Jamtland_VA  3.2%
82                Ingrian                 Croatia_Sipar  1.3%
83                Ingrian               Poland_Balczewo  1.2%
84                Ingrian             Germany_EMedieval    1%
85               Karelian                  Uppsala_Late   41%
86               Karelian              Russia_UstBelaya 20.4%
87               Karelian                   Jamtland_VA  1.8%
88               Karelian             Germany_EMedieval  1.4%
89               Karelian            Sweden_EarlyViking  1.1%
90               Karelian               Poland_Balczewo    1%
91                    Lak              Romania_Medieval 27.5%
92                    Lak            Macedonia_Medieval  8.9%
93                    Lak               Turkey_Medieval  7.8%
94                    Lak Argentina_NorthTierradelFuego  3.2%
95                    Lak                   England_MIA  3.1%
96                    Lak                 Kenya_Kakapel  1.5%
97                    Lak    BosniaHerzegovina_Medieval  1.1%
98                Latvian            Sweden_EarlyViking 58.8%
99                Latvian                 Poland_Santok  5.1%
100               Latvian              Russia_UstBelaya  3.9%
101               Latvian                Poland_Konskie  3.4%
102               Latvian             Poland_Oblaczkowo  2.3%
103               Latvian                Spain_Visigoth  1.6%
104               Latvian                  Uppsala_Late  1.5%
105               Latvian                 Poland_Milicz  1.4%
106               Latvian           Poland_Dziekanowice    1%
107               Latvian                Poland_Niemcza    1%
108               Latvian               Poland_Balczewo    1%
109         Lithuanian_PA            Sweden_EarlyViking 14.6%
110         Lithuanian_PA                 Poland_Milicz  5.7%
111         Lithuanian_PA                 Poland_Santok  5.2%
112         Lithuanian_PA                Poland_Konskie  4.6%
113         Lithuanian_PA           Poland_Dziekanowice  3.1%
114         Lithuanian_PA             Poland_Oblaczkowo  3.1%
115         Lithuanian_PA                Poland_Niemcza  2.8%
116         Lithuanian_PA               Poland_Balczewo  2.8%
117         Lithuanian_PA              Russia_UstBelaya  2.2%
118         Lithuanian_PA                    Poland_Lad  2.1%
119         Lithuanian_PA                 Poland_Ostrow    2%
120         Lithuanian_PA          Mongolia_Uvurkhangai  1.4%
121         Lithuanian_PA             Germany_EMedieval  1.3%
122         Lithuanian_PA                Serbia_Naissus  1.3%
123         Lithuanian_PA                  Uppsala_Late  1.2%
124         Lithuanian_PA                   Jamtland_VA  1.1%
125         Lithuanian_PA                Serbia_Sirmium  1.1%
126         Lithuanian_PA                Spain_Visigoth  1.1%
127         Lithuanian_PZ            Sweden_EarlyViking 55.4%
128         Lithuanian_PZ                 Poland_Santok  8.3%
129         Lithuanian_PZ                Spain_Visigoth  2.5%
130         Lithuanian_PZ              Russia_UstBelaya  2.1%
131         Lithuanian_PZ                Poland_Konskie  1.9%
132         Lithuanian_PZ             Poland_Oblaczkowo  1.7%
133         Lithuanian_PZ                    Poland_Lad  1.4%
134         Lithuanian_PZ               Poland_Balczewo  1.4%
135         Lithuanian_PZ                    Uppsala_IA  1.4%
136         Lithuanian_PZ                Poland_Niemcza  1.1%
137         Lithuanian_RA            Sweden_EarlyViking 28.7%
138         Lithuanian_RA                Poland_Konskie 10.2%
139         Lithuanian_RA             Poland_Oblaczkowo  5.2%
140         Lithuanian_RA                 Poland_Santok  3.7%
141         Lithuanian_RA                 Poland_Milicz  2.7%
142         Lithuanian_RA                Serbia_Sirmium  2.6%
143         Lithuanian_RA           Poland_Dziekanowice  2.6%
144         Lithuanian_RA               Poland_Balczewo  2.5%
145         Lithuanian_RA          Mongolia_Uvurkhangai  2.1%
146         Lithuanian_RA              Russia_UstBelaya    2%
147         Lithuanian_RA                Spain_Visigoth  1.9%
148         Lithuanian_RA                    Poland_Lad  1.8%
149         Lithuanian_RA                Poland_Niemcza  1.5%
150         Lithuanian_RA                 Poland_Ostrow  1.1%
151         Lithuanian_SZ            Sweden_EarlyViking 73.6%
152         Lithuanian_SZ                 Poland_Santok  5.7%
153         Lithuanian_SZ             Poland_Oblaczkowo  1.8%
154         Lithuanian_SZ                Poland_Konskie  1.7%
155         Lithuanian_VA            Sweden_EarlyViking 78.5%
156         Lithuanian_VA                Poland_Konskie  5.3%
157         Lithuanian_VA                 Poland_Santok  1.4%
158         Lithuanian_VZ            Sweden_EarlyViking 49.4%
159         Lithuanian_VZ                 Poland_Santok  5.3%
160         Lithuanian_VZ             Poland_Oblaczkowo  3.4%
161         Lithuanian_VZ                Spain_Visigoth  3.4%
162         Lithuanian_VZ                Poland_Niemcza    2%
163         Lithuanian_VZ                 Poland_Milicz  1.8%
164         Lithuanian_VZ                    Poland_Lad  1.5%
165         Lithuanian_VZ                Poland_Konskie  1.5%
166         Lithuanian_VZ               Poland_Balczewo  1.5%
167         Lithuanian_VZ                    Uppsala_IA  1.3%
168         Lithuanian_VZ          Mongolia_Uvurkhangai  1.3%
169         Lithuanian_VZ                  Uppsala_Late    1%
170        North_Ossetian              Romania_Medieval 65.5%
171        North_Ossetian            Macedonia_Medieval  6.6%
172        North_Ossetian               Turkey_Medieval  4.8%
173        North_Ossetian Argentina_NorthTierradelFuego  2.2%
174              Ossetian              Romania_Medieval 58.1%
175              Ossetian               Turkey_Medieval 13.6%
176              Ossetian Argentina_NorthTierradelFuego  3.2%
177              Ossetian              Lebanon_EjJaouze  1.5%
178                Polish                Poland_Konskie 18.7%
179                Polish              Russia_UstBelaya 14.4%
180                Polish           Poland_Dziekanowice  2.6%
181                Polish                Poland_Niemcza  2.1%
182                Polish               Poland_Balczewo  1.7%
183                Polish                    Poland_Lad  1.5%
184                Polish            Sweden_EarlyViking  1.3%
185                Polish                 Poland_Ostrow  1.3%
186                Polish                Serbia_Naissus  1.3%
187                Polish                  Uppsala_Late  1.1%
188                Polish                 Croatia_Sipar  1.1%
189      Polish_Kashubian                Poland_Konskie    7%
190      Polish_Kashubian                 Poland_Santok  5.2%
191      Polish_Kashubian            Sweden_EarlyViking  4.9%
192      Polish_Kashubian                Serbia_Naissus  4.6%
193      Polish_Kashubian                    Poland_Lad  3.6%
194      Polish_Kashubian               Poland_Balczewo  3.4%
195      Polish_Kashubian          Mongolia_Uvurkhangai  3.2%
196      Polish_Kashubian             Poland_Oblaczkowo  2.9%
197      Polish_Kashubian                   Jamtland_VA  2.4%
198      Polish_Kashubian                Poland_Niemcza  2.2%
199      Polish_Kashubian           Poland_Dziekanowice  2.1%
200      Polish_Kashubian           Denmark_EarlyViking    2%
201      Polish_Kashubian             Germany_EMedieval    2%
202      Polish_Kashubian              Ukraine_Medieval  1.9%
203      Polish_Kashubian                England_Viking  1.7%
204      Polish_Kashubian                 Poland_Legowo  1.6%
205      Polish_Kashubian                 Croatia_Sipar  1.2%
206      Polish_Kashubian                  Uppland_Late  1.1%
207      Polish_Kashubian                 Poland_Milicz  1.1%
208       Polish_Silesian           Denmark_EarlyViking 20.2%
209       Polish_Silesian           Poland_Dziekanowice  3.8%
210       Polish_Silesian              Russia_UstBelaya  3.6%
211       Polish_Silesian                 Croatia_Sipar  1.5%
212       Polish_Silesian                  Uppsala_Late  1.4%
213       Polish_Silesian               Poland_Balczewo  1.1%
214       Polish_Silesian                Serbia_Sirmium    1%
215      Russian_Belgorod                  Uppsala_Late 13.3%
216      Russian_Belgorod              Russia_UstBelaya  8.4%
217      Russian_Belgorod                 Poland_Milicz  5.1%
218      Russian_Belgorod           Poland_Dziekanowice  4.3%
219      Russian_Belgorod          Mongolia_Uvurkhangai    4%
220      Russian_Belgorod                Poland_Konskie  3.4%
221      Russian_Belgorod                    Poland_Lad  2.8%
222      Russian_Belgorod                   Jamtland_VA  2.8%
223      Russian_Belgorod               Poland_Balczewo  1.7%
224      Russian_Belgorod                 Poland_Ostrow  1.5%
225      Russian_Belgorod                Serbia_Naissus  1.5%
226      Russian_Belgorod                Poland_Niemcza  1.5%
227      Russian_Belgorod             Poland_Oblaczkowo  1.5%
228        Russian_Kaluga                  Uppsala_Late 24.7%
229        Russian_Kaluga               Poland_Balczewo  3.9%
230        Russian_Kaluga                 Poland_Legowo  3.7%
231        Russian_Kaluga            Sweden_EarlyViking  3.7%
232        Russian_Kaluga              Russia_UstBelaya  3.2%
233        Russian_Kaluga           Poland_Dziekanowice  1.9%
234        Russian_Kaluga                 Poland_Milicz  1.5%
235        Russian_Kaluga                Serbia_Sirmium  1.5%
236        Russian_Kaluga          Mongolia_Uvurkhangai  1.4%
237        Russian_Kaluga                Poland_Niemcza  1.4%
238        Russian_Kaluga                    Poland_Lad  1.2%
239        Russian_Kaluga              Ukraine_Medieval  1.2%
240        Russian_Kaluga                Serbia_Naissus  1.2%
241        Russian_Kaluga                  Poland_Rumin  1.1%
242        Russian_Kaluga                  Croatia_MLBA    1%
243      Russian_Kostroma                  Uppsala_Late 88.2%
244      Russian_Kostroma              Russia_UstBelaya  1.7%
245  Russian_Krasnoborsky                  Uppsala_Late 80.6%
246  Russian_Krasnoborsky              Russia_UstBelaya  1.5%
247         Russian_Kursk                  Uppsala_Late 35.4%
248         Russian_Kursk              Russia_UstBelaya 16.7%
249         Russian_Kursk            Sweden_EarlyViking 10.4%
250         Russian_Kursk               Poland_Balczewo  2.6%
251         Russian_Kursk                 Poland_Milicz  1.5%
252         Russian_Kursk          Mongolia_Uvurkhangai  1.1%
253   Russian_Leshukonsky                  Uppsala_Late 94.1%
254          Russian_Orel                  Uppsala_Late 31.5%
255          Russian_Orel              Russia_UstBelaya  4.9%
256          Russian_Orel            Sweden_EarlyViking  4.6%
257          Russian_Orel          Mongolia_Uvurkhangai    3%
258          Russian_Orel                    Poland_Lad  2.8%
259          Russian_Orel               Poland_Balczewo  2.4%
260          Russian_Orel                Poland_Konskie  1.8%
261          Russian_Orel                Poland_Niemcza  1.7%
262          Russian_Orel                 Poland_Milicz  1.6%
263          Russian_Orel                 Poland_Ostrow  1.3%
264          Russian_Orel           Poland_Dziekanowice  1.3%
265          Russian_Orel             Poland_Oblaczkowo  1.2%
266          Russian_Orel                   Jamtland_VA    1%
267        Russian_Pinega                  Uppsala_Late 31.5%
268        Russian_Pinega            Sweden_EarlyViking  6.3%
269        Russian_Pinega              Russia_UstBelaya  5.1%
270        Russian_Pinega             Germany_EMedieval  2.3%
271        Russian_Pinega               Poland_Balczewo  2.2%
272        Russian_Pinega                    Poland_Lad  1.6%
273        Russian_Pinega                 Croatia_Sipar  1.1%
274        Russian_Pinega                   Jamtland_VA  1.1%
275        Russian_Pinega                Serbia_Naissus  1.1%
276        Russian_Pinega                 Sweden_Viking  1.1%
277        Russian_Pinega                Poland_Niemcza    1%
278        Russian_Pinega              Ukraine_Medieval    1%
279     Russian_Pinezhsky                  Uppsala_Late 81.5%
280     Russian_Pinezhsky              Russia_UstBelaya    2%
281     Russian_Pinezhsky            Sweden_EarlyViking  1.7%
282         Russian_Pskov                  Uppsala_Late 22.1%
283         Russian_Pskov            Sweden_EarlyViking 15.7%
284         Russian_Pskov              Russia_UstBelaya  7.7%
285         Russian_Pskov                Poland_Konskie  3.8%
286         Russian_Pskov               Poland_Balczewo  3.3%
287         Russian_Pskov           Poland_Dziekanowice  3.3%
288         Russian_Pskov                Poland_Niemcza  1.7%
289         Russian_Pskov                    Poland_Lad  1.5%
290         Russian_Pskov                 Croatia_Sipar  1.3%
291        Russian_Ryazan                  Uppsala_Late 28.8%
292        Russian_Ryazan               Poland_Balczewo    5%
293        Russian_Ryazan           Poland_Dziekanowice  2.9%
294        Russian_Ryazan              Russia_UstBelaya  2.5%
295        Russian_Ryazan                 Poland_Milicz  2.3%
296        Russian_Ryazan                    Poland_Lad  2.2%
297        Russian_Ryazan                Poland_Niemcza  1.7%
298        Russian_Ryazan                 Poland_Ostrow  1.7%
299        Russian_Ryazan                 Poland_Legowo  1.2%
300        Russian_Ryazan          Mongolia_Uvurkhangai  1.2%
301        Russian_Ryazan             Germany_EMedieval  1.1%
302      Russian_Smolensk            Sweden_EarlyViking 10.6%
303      Russian_Smolensk                Poland_Konskie  8.6%
304      Russian_Smolensk              Russia_UstBelaya  5.7%
305      Russian_Smolensk               Poland_Balczewo  4.3%
306      Russian_Smolensk          Mongolia_Uvurkhangai  3.1%
307      Russian_Smolensk                    Poland_Lad  2.8%
308      Russian_Smolensk                Poland_Niemcza  2.7%
309      Russian_Smolensk           Poland_Dziekanowice  2.2%
310      Russian_Smolensk             Poland_Oblaczkowo  2.2%
311      Russian_Smolensk                  Uppsala_Late    2%
312      Russian_Smolensk             Germany_EMedieval  1.8%
313      Russian_Smolensk                 Croatia_Sipar  1.5%
314      Russian_Smolensk                 Poland_Ostrow  1.4%
315      Russian_Smolensk                Serbia_Naissus  1.3%
316      Russian_Smolensk                 Poland_Legowo  1.2%
317      Russian_Smolensk                 Poland_Milicz  1.2%
318      Russian_Smolensk                  Poland_Rumin    1%
319          Russian_Tver                  Uppsala_Late 83.9%
320          Russian_Tver              Russia_UstBelaya  1.6%
321       Russian_Voronez                  Uppsala_Late 23.9%
322       Russian_Voronez              Russia_UstBelaya    8%
323       Russian_Voronez            Sweden_EarlyViking  5.2%
324       Russian_Voronez                Poland_Konskie  3.1%
325       Russian_Voronez               Poland_Balczewo    3%
326       Russian_Voronez                 Poland_Milicz  1.7%
327       Russian_Voronez                Poland_Niemcza  1.6%
328       Russian_Voronez                    Poland_Lad  1.4%
329       Russian_Voronez                 Poland_Legowo  1.4%
330       Russian_Voronez           Poland_Dziekanowice  1.3%
331       Russian_Voronez          Mongolia_Uvurkhangai  1.3%
332       Russian_Voronez                Serbia_Naissus  1.1%
333       Russian_Voronez                 Poland_Ostrow  1.1%
334     Russian_Yaroslavl                  Uppsala_Late 38.6%
335     Russian_Yaroslavl              Russia_UstBelaya  3.3%
336     Russian_Yaroslavl                Poland_Niemcza  2.3%
337     Russian_Yaroslavl                 Poland_Legowo  2.2%
338     Russian_Yaroslavl          Mongolia_Uvurkhangai  1.5%
339     Russian_Yaroslavl           Poland_Dziekanowice  1.4%
340     Russian_Yaroslavl                 Poland_Ostrow  1.4%
341     Russian_Yaroslavl               Poland_Balczewo  1.2%
342     Russian_Yaroslavl                    Poland_Lad  1.2%
343     Russian_Yaroslavl                Serbia_Sirmium    1%
344               Serbian          Mongolia_Uvurkhangai  6.3%
345               Serbian                   Italy_Lazio  4.4%
346               Serbian                Serbia_Naissus  2.9%
347               Serbian    BosniaHerzegovina_Medieval    2%
348               Serbian           Poland_Dziekanowice  1.6%
349               Serbian             Bolivia_Totocachi  1.2%
350               Serbian                  Croatia_Metz  1.1%
351               Serbian       Slovakia_TesarkeMlynany  1.1%
352               Serbian                  Poland_Rumin  1.1%
353               Serbian     Turkey_SoutheastByzantine    1%
354   Ukrainian_Chernihiv            Sweden_EarlyViking 17.8%
355   Ukrainian_Chernihiv                Poland_Konskie 10.7%
356   Ukrainian_Chernihiv              Russia_UstBelaya  7.7%
357   Ukrainian_Chernihiv                  Uppsala_Late  4.7%
358   Ukrainian_Chernihiv           Poland_Dziekanowice  3.1%
359   Ukrainian_Chernihiv               Poland_Balczewo  2.9%
360   Ukrainian_Chernihiv          Mongolia_Uvurkhangai  2.7%
361   Ukrainian_Chernihiv                 Poland_Milicz  2.5%
362   Ukrainian_Chernihiv             Poland_Oblaczkowo    2%
363   Ukrainian_Chernihiv                    Poland_Lad  1.9%
364   Ukrainian_Chernihiv                Poland_Niemcza  1.8%
365      Ukrainian_Dnipro              Russia_UstBelaya 12.8%
366      Ukrainian_Dnipro                  Uppsala_Late  8.4%
367      Ukrainian_Dnipro                Poland_Konskie  4.5%
368      Ukrainian_Dnipro            Sweden_EarlyViking    4%
369      Ukrainian_Dnipro           Poland_Dziekanowice  3.4%
370      Ukrainian_Dnipro          Mongolia_Uvurkhangai  2.6%
371      Ukrainian_Dnipro               Poland_Balczewo  2.2%
372      Ukrainian_Dnipro                Poland_Niemcza    2%
373      Ukrainian_Dnipro                    Poland_Lad  1.9%
374      Ukrainian_Dnipro                 Poland_Milicz  1.7%
375      Ukrainian_Dnipro                 Poland_Ostrow  1.5%
376      Ukrainian_Dnipro             Poland_Oblaczkowo  1.5%
377      Ukrainian_Dnipro                   Jamtland_VA  1.3%
378      Ukrainian_Dnipro                Serbia_Naissus    1%
379        Ukrainian_Lviv                Poland_Konskie  8.6%
380        Ukrainian_Lviv              Russia_UstBelaya  4.3%
381        Ukrainian_Lviv                  Uppsala_Late  3.7%
382        Ukrainian_Lviv               Poland_Balczewo  3.2%
383        Ukrainian_Lviv           Poland_Dziekanowice  2.9%
384        Ukrainian_Lviv          Mongolia_Uvurkhangai  1.9%
385        Ukrainian_Lviv            Sweden_EarlyViking  1.9%
386        Ukrainian_Lviv                    Poland_Lad  1.8%
387        Ukrainian_Lviv                Poland_Niemcza  1.8%
388        Ukrainian_Lviv                 Poland_Milicz  1.4%
389        Ukrainian_Lviv                 Poland_Ostrow  1.2%
390        Ukrainian_Lviv                Serbia_Naissus  1.2%
391        Ukrainian_Lviv          Russia_SaltovoMayaki  1.1%
392        Ukrainian_Lviv    BosniaHerzegovina_Medieval    1%
393       Ukrainian_Rivne                Poland_Konskie   17%
394       Ukrainian_Rivne              Russia_UstBelaya  8.2%
395       Ukrainian_Rivne            Sweden_EarlyViking  7.1%
396       Ukrainian_Rivne           Poland_Dziekanowice  4.4%
397       Ukrainian_Rivne               Poland_Balczewo    3%
398       Ukrainian_Rivne                Poland_Niemcza  2.5%
399       Ukrainian_Rivne                  Uppsala_Late    2%
400       Ukrainian_Rivne                    Poland_Lad    2%
401       Ukrainian_Rivne          Mongolia_Uvurkhangai  1.5%
402       Ukrainian_Rivne                 Poland_Milicz  1.5%
403       Ukrainian_Rivne             Germany_EMedieval  1.4%
404       Ukrainian_Rivne                 Poland_Ostrow  1.4%
405       Ukrainian_Rivne                Serbia_Naissus    1%
406        Ukrainian_Sumy                  Uppsala_Late 13.9%
407        Ukrainian_Sumy                Poland_Konskie  7.7%
408        Ukrainian_Sumy                    Poland_Lad  4.2%
409        Ukrainian_Sumy          Mongolia_Uvurkhangai    3%
410        Ukrainian_Sumy            Sweden_EarlyViking    3%
411        Ukrainian_Sumy           Poland_Dziekanowice  2.5%
412        Ukrainian_Sumy              Russia_UstBelaya  2.4%
413        Ukrainian_Sumy                Poland_Niemcza  2.3%
414        Ukrainian_Sumy               Poland_Balczewo  2.2%
415        Ukrainian_Sumy                 Poland_Milicz  1.8%
416        Ukrainian_Sumy                  Poland_Rumin  1.4%
417        Ukrainian_Sumy             Poland_Oblaczkowo  1.4%
418        Ukrainian_Sumy                 Poland_Ostrow  1.2%
419        Ukrainian_Sumy                 Poland_Legowo  1.1%
420        Ukrainian_Sumy             Germany_EMedieval    1%
421        Ukrainian_Sumy                Serbia_Naissus    1%
422        Ukrainian_Sumy                   Jamtland_VA    1%
423 Ukrainian_Zakarpattia                Serbia_Naissus  7.3%
424 Ukrainian_Zakarpattia            Sweden_EarlyViking    4%
425 Ukrainian_Zakarpattia                  Uppsala_Late  3.5%
426 Ukrainian_Zakarpattia           Poland_Dziekanowice  3.2%
427 Ukrainian_Zakarpattia                Poland_Konskie  2.9%
428 Ukrainian_Zakarpattia          Mongolia_Uvurkhangai  2.8%
429 Ukrainian_Zakarpattia              Russia_UstBelaya  1.6%
430 Ukrainian_Zakarpattia               Poland_Balczewo  1.4%
431 Ukrainian_Zakarpattia          Russia_SaltovoMayaki  1.2%
432 Ukrainian_Zakarpattia                 Poland_Ostrow  1.1%
433 Ukrainian_Zakarpattia                Poland_Niemcza    1%
434    Ukrainian_Zhytomyr            Sweden_EarlyViking  4.8%
435    Ukrainian_Zhytomyr           Poland_Dziekanowice  4.7%
436    Ukrainian_Zhytomyr               Poland_Balczewo  4.5%
437    Ukrainian_Zhytomyr              Russia_UstBelaya  3.7%
438    Ukrainian_Zhytomyr                    Poland_Lad  3.2%
439    Ukrainian_Zhytomyr                Poland_Konskie    3%
440    Ukrainian_Zhytomyr                Poland_Niemcza  2.5%
441    Ukrainian_Zhytomyr                  Uppsala_Late  2.2%
442    Ukrainian_Zhytomyr                 Poland_Milicz    2%
443    Ukrainian_Zhytomyr                 Poland_Legowo  1.7%
444    Ukrainian_Zhytomyr          Mongolia_Uvurkhangai  1.7%
445    Ukrainian_Zhytomyr                 Poland_Ostrow  1.6%
446    Ukrainian_Zhytomyr                Serbia_Naissus  1.5%
447    Ukrainian_Zhytomyr             Poland_Oblaczkowo  1.4%
448    Ukrainian_Zhytomyr                 Croatia_Sipar  1.3%
449    Ukrainian_Zhytomyr                   Jamtland_VA  1.2%
450    Ukrainian_Zhytomyr             Germany_EMedieval    1%
451    Ukrainian_Zhytomyr                Serbia_Sirmium    1%
452  Ukrainian_Zhytomyr_o                   Italy_Lazio 94.3%

options(repr.plot.width = 12, repr.plot.height = 12, repr.plot.res = 400)

plotfun(mprd %>% sample_n(16),lsz = 2,nrw = 4)

myd = as_tibble(import("../Raw Data/Archeological Samples/aDNA-Y-mt/all-ancient-dna.xlsx"))

Warning message:
“Expecting numeric in AA1070 / R1070C27: got '...'”
Warning message:
“Expecting numeric in AA1476 / R1476C27: got '...'”
Warning message:
“Expecting numeric in AA1477 / R1477C27: got '...'”
Warning message:
“Expecting numeric in AO2887 / R2887C41: got '..'”
Warning message:
“Expecting numeric in AA4167 / R4167C27: got '...'”
Warning message:
“Expecting numeric in AO5085 / R5085C41: got '..'”
Warning message:
“Coercing text to numeric in AO7537 / R7537C41: '0.088'”
Warning message:
“Expecting numeric in AO8135 / R8135C41: got '..'”
Warning message:
“Expecting numeric in AO8222 / R8222C41: got '..'”
Warning message:
“Expecting numeric in AO8246 / R8246C41: got '..'”
Warning message:
“Expecting numeric in AO11704 / R11704C41: got '..'”
Warning message:
“Expecting numeric in AO11886 / R11886C41: got '..'”
Warning message:
“Coercing text to numeric in AO14505 / R14505C41: '0.778'”

bad = as_tibble(import("../Genetics/G25/Data/CSV/Eurasia/G25_BA.csv"))
iad = as_tibble(import("../Genetics/G25/Data/CSV/Eurasia/G25_IA.csv"))
mad = as_tibble(import("../Genetics/G25/Data/CSV/Eurasia/G25_MA.csv"))

myd %>% sample_n(5)

myptrna = "(?<=:).+$"
myptrnb = "^\\w+?_\\w+?(?=[_:\\.])"
bad = bad %>% mutate(label = str_extract(sample,myptrnb),sample = str_extract(sample,myptrna),.before = V2)
iad = iad %>% mutate(label = str_extract(sample,myptrnb),sample = str_extract(sample,myptrna),.before = V2)
mad = mad %>% mutate(label = str_extract(sample,myptrnb),sample = str_extract(sample,myptrna),.before = V2)

mad %>% sample_n(5)

mydd = mad %>% left_join(myd,by = c("sample" = "Object-ID"))

mydd %>% sample_n(5) %>% select(sample,label,Simplified_Culture,Culture_Grouping,Label,Location,Country,Mean)

mydd %>% count(Culture_Grouping,sort = TRUE)

mydd = mydd %>% dplyr::filter(Mean > 600,Mean < 1400)

mydd = mydd %>% 
        mutate(sample = ifelse(is.na(Location),label,paste(Culture_Grouping,Location,sep = "_"))) %>% 
        #mutate(sample = ifelse(is.na(Label),label,Label)) %>% #paste(Country,str_remove_all(Location,"[[:punct:]]"),sep = "_"))) %>% 
        mutate(sample = str_extract(sample,"^\\w{3,12}")) %>% 
        select(sample,all_of(matches("^V\\d")))

dim(mydd)
mydd %>% sample_n(5)

mdl = myfun(na.omit(mydd),e = 1,a = 0,l = 15)

[1] "Number of classes: 155"
[1] "Split into test and train samples"
[1] 726  26
[1] 243  26
[1] "Starting XGBoost training"
[1]	train-mlogloss:3.875224	test-mlogloss:4.069648 
[26]	train-mlogloss:1.833329	test-mlogloss:2.962411 
[51]	train-mlogloss:1.288812	test-mlogloss:2.933635 
[76]	train-mlogloss:1.045214	test-mlogloss:2.947281 
[100]	train-mlogloss:0.912106	test-mlogloss:2.991623 
# A tibble: 15 × 5
     row label variable  value maxval
   <int> <dbl> <chr>     <dbl>  <dbl>
 1   119    92 47       0.0505 0.0505
 2    85    56 11       0.0799 0.0799
 3   220   153 153      0.832  0.832 
 4   236   154 153      0.244  0.244 
 5    97    37 37       0.0333 0.0333
 6     8   153 153      0.354  0.354 
 7   219   153 153      0.445  0.445 
 8   111    42 153      0.602  0.602 
 9   133   153 153      0.736  0.736 
10   224   144 145      0.129  0.129 
11   128    67 94       0.0353 0.0353
12   115    50 145      0.195  0.195 
13   194   135 153      0.467  0.467 
14    77    33 153      0.497  0.497 
15   223   143 145      0.378  0.378 
[1] "test-error = 0.650205761316872"

mprd = mypfun(mdl,na.omit(mydd),ppl)

[1] "Using 155 populations"

Joining with `by = join_by(variable)`

   name          eth  value
1    MD  Uyghur_Olon  5.13%
2    MD Muslim_Plaza  2.73%
3    MD BosniaHerzeg  2.48%
4    MN  Uyghur_Olon  4.87%
5    MN    Longobard  2.96%
6    MN Chilpek_800C  2.61%
7    MN BosniaHerzeg   2.2%
8    MN Lebanon_Chhi  2.19%
9    MN        Early 19.68%
10   RN  Uyghur_Olon  4.05%
11   RN BosniaHerzeg  3.39%
12   RN Lebanon_Chhi  2.97%
13   TP Uppland_Late  9.94%
14   TP Poland_Marko  6.94%
15   TP Late_Norse_W  5.51%
16   TP Poland_Niemc   4.9%
17   TP Poland_Plons  3.45%
18   TP  Italy_Lazio  2.67%
19   TP Poland_Rumin  2.29%

mprd = mypfun2(mdl,na.omit(mydd),ppl)

[1] "Using 155 populations"

Joining with `by = join_by(variable)`

[1] "Using 155 populations"

Joining with `by = join_by(variable)`

[1] "Using 155 populations"

Joining with `by = join_by(variable)`

[1] "Using 155 populations"

Joining with `by = join_by(variable)`

[1] "Using 155 populations"

Joining with `by = join_by(variable)`

plotfun3(mprd)

Warning message:
“ggrepel: 6 unlabeled data points (too many overlaps). Consider increasing max.overlaps”

sample	V2	V3	V4	V5	V6	V7	V8	V9	V10	⋯	V17	V18	V19	V20	V21	V22	V23	V24	V25	V26
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
Aidonia_LBA.rel:AID002	0.126344	0.158423	-0.001131	-0.05814	0.026159	-0.025937	-0.00188	-0.001154	0.002454	⋯	-0.006364	0.008345	-0.001774	0.002514	-0.005002	-0.006114	-0.004575	0.000986	-0.001566	-0.00455

sample	V2	V3	V4	V5	V6	V7	V8	V9	V10	⋯	V17	V18	V19	V20	V21	V22	V23	V24	V25	V26
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
Albania_BA_IA:I14688	0.119514	0.160454	0.02225	-0.028101	0.024312	-0.017012	0.00141	-0.001385	-0.001841	⋯	-0.016176	-0.008736	0.003674	0.003645	-0.004502	-0.013726	0.009645	-0.001849	0.011809	-0.011855

sample	V2	V3	V4	V5	V6	V7	V8	V9	V10	⋯	V17	V18	V19	V20	V21	V22	V23	V24	V25	V26
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
Albania_Medieval:I13839	0.125205	0.153345	0.016216	-0.036176	0.03139	-0.013108	0	0.002077	0.007772	⋯	-0.01074	0.008996	0.004307	0.006536	-0.016508	-0.007237	0.001113	0.005053	-0.001205	0.001676

sample	PC1	PC2	PC3	PC4	PC5	PC6	PC7	PC8	PC9	⋯	PC16	PC17	PC18	PC19	PC20	PC21	PC22	PC23	PC24	PC25
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
Abazin:KCHE-1032	0.10927	0.072103	-0.023004	-0.016796	-0.028005	0.003347	0.003055	-0.010384	-0.049904	⋯	-0.01074	-0.001173	-0.004054	-0.006662	0.023386	0.004742	-0.000124	-0.000863	-0.010965	-0.001916

V1	V2	V3	V4	V5	V6	V7	V8	V9	V10	⋯	V17	V18	V19	V20	V21	V22	V23	V24	V25	V26
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
RN:RN2020	0.100164	0.135065	-0.003771	-0.041667	0.009540	-0.017570	-0.004465	-0.003000	0.008590	⋯	-0.013657	-0.016168	0.003801	0.001508	-0.005378	-0.002870	-0.002226	-0.001109	-0.002771	-0.005987
TP:TP2022	0.127482	0.125926	0.072407	0.060724	0.033852	0.024821	0.010340	0.006692	-0.005931	⋯	0.007292	0.004955	-0.000380	0.004274	0.004877	-0.008610	-0.001978	0.006532	-0.006266	-0.001676
MN:MN2020	0.097888	0.141159	-0.002640	-0.051034	0.009540	-0.017012	-0.007285	0.000000	0.006954	⋯	-0.005701	-0.017732	0.002660	-0.002388	-0.004002	0.000749	-0.007048	-0.002095	0.003976	-0.000120
MD:MD2022	0.099026	0.129988	-0.001886	-0.041667	0.011079	-0.015060	0.002350	0.001846	0.011862	⋯	-0.003978	0.001956	0.000380	-0.000628	-0.005753	-0.006738	-0.001978	-0.001849	-0.001807	-0.008143

sample	n
<chr>	<int>
Dutch	166
Swedish	101
Greek_Crete	100
Irish	85
Danish	81
German	79
German_Erlangen	67
Lak	52
Moldovan	42
Polish	41
French_Alsace	40
French_Brittany	40
Norwegian	40
Mongol_IMAR	39
French_Occitanie	36
French_Nord	33
Karelian	33
Tunisian_Douz	33
Bashkir	31
Greek_Laconia	31

sample	n
<chr>	<int>
Czech_EBA	100
Poland_Trzciniec	66
Czech_CordedWare	41
Czech_BellBeaker	34
Armenia_LBA	30
England_BellBeaker	27
Serbia_Mokrin	27
Israel_MLBA	26
Sweden_Gotland	26
Turkey_EBA	26

sample	n
<chr>	<int>
England_MIA	122
Armenia_LBA	42
England_EIA	32
England_EastYorkshire	30
Mongolia_EIA	25
Czech_IA	23
Poland_Kowalewko	23
Kazakhstan_Tasmola	19
Iran_Hasanlu	18
Italy_Tuscany	18

sample	n
<chr>	<int>
Sweden_Viking	118
England_EarlyMedieval	89
Denmark_Viking	68
Italy_Medieval	38
Estonia_EarlyViking	34
Ireland_Kilteasheen	30
England_Viking	29
Vladimir_MA	28
Mongolia_Arkhangai	26
Norway_Viking	26

Culture_Grouping	n
<chr>	<int>
NA	414
Viking Sweden	118
Viking Denmark	68
Mongol	49
Early_Viking	42
Viking UK	28
Viking Norway	26
Viking Russia	26
Longobard Kingdom	20
Viking Iceland	16
Late Xiongnu	14
Medieval	13
Early_Norse	12
Uyghur	11
Early Xiongnu	10
Anglo-Saxon Early Period	8
Anglo-Saxon Middle Period	8
Germany Medieval	7
Viking Poland	7
Lebanon Middle Ages	6
Türk	6
North East Iberia Medieval	5
Fatyanovo Boshnevo	4
Guanche_mummy	4
Sardinia Medieval	4
Viking Ireland	4
Viking Orkney	4
Khitan	3
Late_Norse	3
Early Middle Ages	2
Muslim	2
Viking Ukraine	2
"La Tène"	1
Apulia Early Iron Age	1
Bavarian	1
Bulgaria_EBA_EIA	1
Chilpek_800CE	1
Cis-Baikal Medieval	1
Heishui_Mohe_EarlyMedieval	1
High Middle Ages	1
Hungary Avar Late	1
Hungary Medieval	1
Kayalyk_950CE	1
Mongolia_LBA_Ulaanzukh	1
Old Bering Sea	1
Pict Orkney	1
SE_Iberia_c.5-8CE	1
Saltovo-Mayaki	1
Sardinia_LateAntiquity	1
Slab Grave	1
Turk	1
Unclassified	1
Ust'-Belaya medieval	1
Viking Faroes	1
Viking IsleOfMan	1
Viking Wales	1

A tibble: 10 × 26
V1	V2	V3	V4	V5	V6	V7	V8	V9	V10	⋯	V17	V18	V19	V20	V21	V22	V23	V24	V25	V26
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
Lithuanian_VA:average	0.1344249	0.1257226	0.0824762	0.0750975	0.0433311	0.0278890	0.0099878	0.0148840	-0.0020454	⋯	0.0029435	0.0061411	-0.0005702	0.0023129	0.0061155	-0.0037310	-0.0048100	0.0072346	-0.0078805	-0.0008622
Ukrainian_Zhytomyr:average	0.1313841	0.1272314	0.0710604	0.0592936	0.0371497	0.0232674	0.0104747	0.0132521	-0.0029216	⋯	-0.0041293	0.0045820	-0.0006336	0.0036631	0.0006433	-0.0078433	-0.0031266	0.0046306	-0.0027714	0.0019331
Ashkenazi_Belarussia:average	0.1019155	0.1339716	-0.0073393	-0.0395799	0.0107712	-0.0144595	-0.0010123	-0.0010294	0.0057267	⋯	0.0027944	0.0018154	-0.0003409	0.0014889	-0.0012602	-0.0038586	-0.0007705	0.0027399	0.0015665	-0.0002949
Ashkenazi_Lithuania:average	0.0998539	0.1327575	-0.0092224	-0.0403750	0.0094843	-0.0141475	-0.0005555	-0.0011750	0.0060613	⋯	0.0034595	0.0016001	0.0001612	0.0004455	-0.0031721	-0.0032555	-0.0033497	0.0029245	0.0024428	-0.0010560
Serbian:average	0.1273334	0.1372290	0.0400240	0.0148299	0.0314974	0.0045957	0.0048738	0.0066720	-0.0011737	⋯	-0.0008358	0.0040476	0.0005894	0.0043011	-0.0024468	-0.0083168	-0.0017151	0.0048925	0.0003720	-0.0020097
Cossack_Ukrainian:average	0.1354490	0.1167860	0.0716530	0.0600780	0.0338520	0.0231480	0.0112810	0.0106150	0.0030680	⋯	0.0019890	0.0003910	0.0051940	0.0035200	0.0033770	-0.0096080	-0.0023490	0.0040670	-0.0068680	0.0005990
North_Ossetian:average	0.1041480	0.0888588	-0.0311125	-0.0251132	-0.0383148	0.0057170	0.0117505	-0.0006925	-0.0539945	⋯	-0.0226065	0.0027380	-0.0059542	-0.0098988	0.0188840	0.0060518	0.0019472	-0.0007395	-0.0084048	-0.0027242
Ukrainian_Rivne:average	0.1301377	0.1243461	0.0702284	0.0625543	0.0392208	0.0211027	0.0096616	0.0104867	-0.0003636	⋯	-0.0009428	0.0055342	-0.0017314	0.0032261	-0.0006670	-0.0049217	-0.0036958	0.0048341	-0.0043109	0.0001066
Ashkenazi_Ukraine:average	0.0994244	0.1351162	-0.0055060	-0.0401166	0.0120483	-0.0142652	-0.0010928	0.0001154	0.0077720	⋯	-0.0018297	-0.0043223	-0.0000190	0.0012758	-0.0046772	-0.0031258	-0.0025904	0.0007702	0.0021028	0.0010059
Polish:average	0.1318405	0.1292694	0.0698685	0.0577382	0.0406754	0.0217127	0.0086781	0.0108626	-0.0009329	⋯	-0.0005595	0.0015455	-0.0000741	0.0026948	0.0012872	-0.0031286	-0.0031185	0.0056063	-0.0033328	-0.0000876

A tibble: 5 × 64
Object-ID	Colloquial-Skeletal	Latitude	Longitude	Sex	mtDNA-coverage	mtFAR	mtDNA-haplogroup	mtDNA-Haplotree	mt-FTDNA	⋯	Location	SiteID	Country	LP	Skin	Hair	Eye	P1104A	Other	Index
<chr>	<chr>	<dbl>	<dbl>	<chr>	<chr>	<dbl>	<chr>	<chr>	<chr>	⋯	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<chr>	<dbl>	<chr>	<dbl>
I1187	CHPKL301N-001	32.97417	35.33139	M	9.3800000000000008	0.3246045	U6d	U6d	https://www.familytreedna.com/public/mt-dna-haplotree/U;name=U6d	⋯	Peqi'in Cave	NA	Israel	NA	NA	NA	NA	NA	NA	5620
Seden	NA	62.10388	131.30859	NA	NA	NA	NA	NA	NA	⋯	Central Yakutia	Seden	Russia	NA	NA	NA	NA	NA	NA	1305
ECS1	NA	47.14789	20.92393	NA	NA	0.1696913	N1a	N1a	https://www.familytreedna.com/public/mt-dna-haplotree/N;name=N1a	⋯	Ecsegfalva 1	NA	Hungary	NA	NA	NA	NA	NA	NA	811
I0418	Kurgan 4, Grave 1, SVP 24	52.91278	50.99056	F	187	0.2496144	T1a1	T1a1	https://www.familytreedna.com/public/mt-dna-haplotree/T;name=T1a1	⋯	Utyevka, Samara River, Samara	Site IV	Russia	NA	NA	NA	NA	NA	NA	3008
HJTW13	..	33.59221	114.02212	M	7.4103399999999997	NA	NA	NA	NA	⋯	HaoJiaTai	NA	China	NA	NA	NA	NA	NA	NA	12440

A tibble: 5 × 27
sample	label	V2	V3	V4	V5	V6	V7	V8	V9	⋯	V17	V18	V19	V20	V21	V22	V23	V24	V25	V26
<chr>	<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
VK435	Sweden_Viking	0.146832	0.137096	0.053551	0.033592	0.047393	0.015897	-0.000235	0.002077	⋯	-0.015513	0.017863	-0.002660	0.005656	0.026638	0.004991	0.008037	0.022061	0.005663	0.023471
R2207.SG	Slovakia_TesarkeMlynany	0.136588	0.135065	0.071276	0.041344	0.032314	0.011156	0.001410	0.002077	⋯	-0.001591	-0.007432	0.006081	0.006034	0.001876	0.013227	0.003462	-0.001849	0.015303	0.001197
SHK002	Vladimir_MA	0.066017	-0.174671	0.042615	-0.000646	-0.038469	-0.003347	0.007755	0.014769	⋯	0.011403	-0.003260	0.003294	0.010936	0.012006	-0.018467	-0.003586	-0.016885	0.002048	-0.000599
I20655	England_EarlyMedieval	0.127482	0.135065	0.075047	0.054264	0.042162	0.021475	0.005170	0.006000	⋯	0.022275	0.013038	0.001014	-0.002514	0.005503	0.011480	-0.003833	0.008381	0.014821	-0.008382
VK352	Sweden_Viking	0.120652	0.124910	0.064111	0.064923	0.036930	0.016455	0.001410	0.009000	⋯	0.008618	-0.004172	0.001647	0.007290	0.004377	0.010606	0.001978	0.004560	0.005181	-0.004311

A tibble: 5 × 26
sample	V2	V3	V4	V5	V6	V7	V8	V9	V10	⋯	V17	V18	V19	V20	V21	V22	V23	V24	V25	V26
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
Poland_Ostro	0.120652	0.119832	0.062602	0.066861	0.047086	0.015618	0.011516	0.010615	0.000409	⋯	-0.014187	-0.013169	-0.003294	0.006536	-0.006503	0.000125	-0.007666	0.013064	0.007953	0.005628
Poland_Ostro	0.133173	0.123895	0.073539	0.077520	0.042469	0.018686	0.006110	0.017307	-0.006340	⋯	0.003713	-0.004172	0.004434	0.002137	-0.003126	-0.012977	-0.007296	0.013434	-0.006989	0.005987
Poland_Niemc	0.119514	0.123895	0.074293	0.066215	0.043700	0.053826	0.020916	0.011307	-0.021270	⋯	0.004906	0.011735	-0.004434	-0.002640	0.001376	-0.001248	0.003091	0.015899	-0.004338	0.021435
Ireland_Kilt	0.133173	0.135065	0.056568	0.054910	0.035699	0.016455	0.002585	0.003461	0.003272	⋯	0.016309	0.008866	0.004054	-0.007793	0.009755	0.008859	0.002597	0.006162	0.012532	0.004670
Viking	0.120652	0.128972	0.061848	0.049742	0.049240	0.016176	-0.000235	0.003000	0.002863	⋯	-0.003978	-0.020340	0.003801	-0.002891	0.006503	0.008111	-0.000247	-0.001725	0.008194	-0.005987